ECCV2026 Paper Notes TODO¶

总计: 1095 篇 | 已完成: 1095 | 待更新: 0

2D Features Are All You Need for 3D Shape Understanding | AC: 5088
2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction | arXiv: 2603.19964 | AC: 4194
340 FPS Reflection-free Video from Spikes Modulated by a Rapidly Rotating Polarizer | AC: 4598
360Anything: Geometry-Free Lifting of Images and Videos to 360° | arXiv: 2601.16192 | AC: 3670
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents | AC: 5213
360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method | AC: 4124
3D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanism | AC: 3820
3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems | arXiv: 2603.02149 | AC: 5956
3D Gaussian Splatting Compression with Object Scalability | AC: 4180
3D Gaussian Texture for Real-time Mesoscale Appearance Synthesis and Rendering | AC: 5185
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement | AC: 4208
3D-Aware VLMs with Implicit and Explicit Geometries | AC: 3224
3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing | AC: 4525
3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification | AC: 5389
3D-ReGen: A Unified 3D Geometry Regeneration Framework | AC: 5538
3DGS3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering | AC: 3945
3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints | AC: 4788
3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering | AC: 5396
4D-VGGT: A SpatioTemporal Foundation Model for Dynamic Scene Geometry Estimation | AC: 3366
4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video | AC: 4866
A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention | AC: 3687
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP | arXiv: 2606.30342 | AC: 4853
A Comprehensive Analysis about Unsupervised Outlier Detection for Images | AC: 5320
A Dual-space Patch-driven Complementary Learning Framework for Semi-supervised Multi-organ Segmentation | AC: 3317
A Dual-Transformer Architecture with Cross-Attention for Multi-Camera View Recommendation | AC: 5242
A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR | arXiv: 2606.31225 | AC: 3216
A Mechanism-Driven Theory of Phase Transitions in Active Learning | arXiv: 2607.00144 | AC: 4856
A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models | AC: 3665
A Scalable Vector Graphics Latent Space | AC: 5250
A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world | arXiv: 2606.21216 | AC: 3432
A second-order theory of texture for depth from focus | AC: 3452
A Simple Baseline with Placement Prior for Point-Supervised Oriented Object Detection | AC: 5334
A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning | AC: 3311
Abstract the Layout, Focus the Detail: A Dual-Granularity Representation Framework for Zero-Shot 3D Visual Grounding | AC: 5726
AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation | arXiv: 2606.31204 | AC: 5183
AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation | AC: 4669
Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation | arXiv: 2606.31323 | AC: 4695
Accelerating Diffusion Models via Equal-Risk Caching | AC: 5300
Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache | AC: 5921
Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction | arXiv: 2606.24156 | AC: 3636
Accelerating Text-to-Video Generation with Calibrated Sparse Attention | AC: 3436
Accurate Zero-shot Quantization via Hierarchical Teacher-Assistant Distillation | AC: 4699
Achieving Subcategorical Erasure in Text-to-Image Models | AC: 4524
ActionParty: Multi-Subject Action Binding in Generative Video Games | AC: 4221
ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning | AC: 5269
Activation Quantization of Vision Encoders Needs Prefixing Registers | AC: 5152
Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction | arXiv: 2603.06852 | AC: 3847
ActiveStructure: Plane Scene Graph-Guided Active 3D Gaussian Splatting | AC: 5184
Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO | AC: 4730
Ada-VNNs: Adaptive Equivariance for Vector Neural Networks | AC: 4500
AdaBoosting Text Prompts for Vision-Language Models | arXiv: 2607.00684 | AC: 4284
AdaBridge-SR: Adaptive Bridge Matching for Real-World Image Super-Resolution | AC: 5676
AdaDexGrasp: Adaptive Dexterous Grasping via 3D Visuo-Tactile Representation Fusion | AC: 5885
ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs | arXiv: 2606.31054 | AC: 5033
Adapting MLLMs for Nuanced Video Retrieval | AC: 4071
Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation | AC: 4115
Adaptive Neural Dynamics for Robust Geometric LiDAR-Inertial State Estimation on UAVs | AC: 3654
Adaptive Noise Covariance Scheduling under Riemannian Metrics for Diffusion Models | AC: 3974
Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection | arXiv: 2606.29029 | AC: 3168
AdaptiveSplat: Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction | AC: 4240
AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking | AC: 4501
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods | arXiv: 2606.24484 | AC: 3683
Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation | AC: 5869
Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution | AC: 4022
AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World | arXiv: 2606.29716 | AC: 4015
AeroVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control | AC: 5844
AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware | arXiv: 2602.16249 | AC: 5712
AffoGato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale | arXiv: 2506.12009 | AC: 4336
Affordance-Guided Diffusion Prior for 3D Hand Reconstruction | AC: 4223
Agent-OBJ: Prompt-Driven 3D Adversaries for Multi-Modal Perception | AC: 5027
Agentic Collaborative Cognition for Zero-Shot 3D Understanding | arXiv: 2606.24649 | AC: 4045
AgentVLN: Towards Agentic Vision-and-Language Navigation | AC: 3693
Aggregating Cross-Domain Knowledge via Learnable Tokens for Multi-Teacher Distillation | AC: 5104
AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors | arXiv: 2603.17975 | AC: 3219
AIMold: An Autonomous AI-based Pipeline for Complex Mold Design | AC: 5227
AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting | AC: 3540
AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision | arXiv: 2604.26567 | AC: 5421
AiSCREAM: Absolute Target Localization with Language-Conditioned Cross-View Alignment for Autonomous Vehicles | AC: 4382
Align and Segment: Unsupervised Learning for Building Segmentation From Misaligned Labels | AC: 5445
Aligning Anything: Hierarchical Motion Estimation for Video Frame Interpolation | AC: 5280
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation | AC: 3296
AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport | AC: 4288
Allo{SR}2: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows | AC: 3463
AlphaRad: Grounded Zero-Shot Classification in Chest Radiology via α-Corrected Binary Cross Entropy and Factorized Latent Supervision | AC: 3412
AMCI: Unlock the Potential of Large Multimodal Models for Fine-grained Open-world Classification via Adaptive Memory Context Injection | AC: 3437
AMCoNav: Asynchronous Multi-module Collaborative Framework for Embodied Visual Navigation | AC: 5222
Amplify, Aggregate, and Adjust: VideoMAE-based Holistic-Subtle Aggregation for Micro-Action Recognition | AC: 4219
An Inverse-Adversarial and Difficulty-Adaptive Robust Vision-Language Model | AC: 3380
Analytic Bayesian Uncertainty for LiDAR Segmentation: A Single-pass Generative Approach | AC: 5831
Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models | AC: 3912
AnaPFL: When Closed-Form Solutions Meet Generalizationand Personalization in Personalized Federated Learning | AC: 4595
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models | AC: 4828
Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion | AC: 3196
Anchored, Not Graded: How Vision-Language Models Fail at Slant-from-Texture Perception | arXiv: 2606.06714 | AC: 4561
AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation | AC: 4292
Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time | AC: 5400
Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer | arXiv: 2606.31089 | AC: 3284
AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning | AC: 4172
AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting | AC: 4233
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories | AC: 5000
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution | AC: 4173
ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID | AC: 5111
Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection | AC: 4995
Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation | AC: 3308
Any to Full: Prompting Depth Anything for Depth Completion in One Stage | AC: 3803
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation | AC: 5144
AnyGround3D: Towards Grounding Any 3D Object in the Wild via 2D-to-3D Lifting | AC: 3160
AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images | arXiv: 2606.31077 | AC: 5344
AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer | AC: 4851
AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization | arXiv: 2603.17461 | AC: 3579
AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors | AC: 4940
ARC-Loc: Leveraging Azimuthal Ray Convergence as a Geometric Cue for Direct Cross-View Localization | AC: 3676
ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection | AC: 5146
Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection | AC: 3983
Are Video Reasoning Models Ready to Go Outside? | arXiv: 2603.10652 | AC: 4365
ARGENT: Adaptive Hierarchical Image-Text Representations | AC: 5595
ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search | AC: 4039
ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions | AC: 5555
Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations | AC: 5435
ART-VSR: Adaptive Rectified Trajectories for One-Step Video Super-Resolution | AC: 4653
Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints | arXiv: 2603.11606 | AC: 3496
ARVAR: Accelerating Visual Autoregressive Model via Attention Retrospect | AC: 3564
ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving | AC: 3354
ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving | arXiv: 2606.29286 | AC: 4652
Asymmetric Anchoring: Opening the Black Box of MLLMs for Forgery Detection | AC: 5294
Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation | AC: 3573
ATOMIC: A Domain-Specific Vision-Language Model for Transmission Electron Microscopy | AC: 5128
ATP-Bench: Towards the Agentic Tool Planning for MLLM Interleaved Generation | AC: 3485
Attention is Case-Sensitive | AC: 3409
Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment | AC: 4363
Attention-based Vision-Language Memory for Spatial Reasoning | AC: 4166
Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning | AC: 4203
Attention-Logit Steering to Compositional Generalization for Continual VQA | AC: 5723
Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models | AC: 3951
Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video | arXiv: 2512.12165 | AC: 4578
Audio-Visual Continual Test-Time Adaptation without Forgetting | AC: 4051
Auto-Prompting: Layer-Specific Prompt Fusion Discovery via Differentiable Search | arXiv: 2606.26379 | AC: 4112
Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens | AC: 4010
AutoSpeed: Annotation-Free Stage-Adaptive Motion Speed Learning for Robot Manipulation | arXiv: 2607.01051 | AC: 3578
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs | AC: 3550
AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing | AC: 4102
AV2T-Gen: Aerial Visible to Thermal Generation with Environment and Vehicle State Guidance | AC: 3919
AViTS：Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation | AC: 3330
AVQ-Attention: Adaptive Vector-Quantized Attention | AC: 4988
AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution | arXiv: 2607.00987 | AC: 5371
AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation | arXiv: 2606.30811 | AC: 5346
A²-Edit: Precise Reference-Guided Image Editing of Arbitrary Objects and Ambiguous Masks | AC: 4028
BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection | AC: 5489
Back-Tracking from Clarity: Self-Learning to See Text from Afar | AC: 3551
Background Blurring Matters: Improving Visual Grounding by Merging Text-Irrelevant Tokens | AC: 5081
BackTranslation2.0 - A Linguistically Motivated Metric to Assess Sign Language Production | arXiv: 2606.28673 | AC: 4935
BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension | AC: 5793
BATQuant: Outlier-Resilient MXFP4 Quantization via Learnable Block-wise Optimization | AC: 4636
Bayesian Self-Attention with Local Pixel Correlations for Lightweight Denoising Transformers | AC: 4718
Bayesian Uncertainty Attribution-Guided Fine-Tuning for Open-Set Action Recognition | AC: 5989
BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models | AC: 5972
Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models | AC: 4638
Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning | AC: 4647
Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset | AC: 4633
Benchmarking Federated Learning & Knowledge Distillation for Point Cloud Classification | AC: 3844
Benchmarking MLLMs on Mistake Recognition and Explanation in Single-Step Components of Cooking | AC: 5187
Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench | AC: 5536
Benchmarking Vision-Language Models for Microscopic Plant Image Understanding | AC: 4108
Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation | AC: 3661
BeTTER: Diagnose the Illusion of Embodied Reasoning in Vision-Language-Action Models | AC: 5364
BEV-GS: Feed-forward Gaussian Splatting in Bird’s-Eye-View for Road Reconstruction | AC: 4436
BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations | AC: 4104
BEVOpen3D: Towards Open-World 3D Object Detection in Bird's-Eye-View | AC: 3368
Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization | AC: 3796
Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment | AC: 4698
Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes | AC: 4433
Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models | AC: 4079
Beyond Attention: Convolutional Global Context for Remote Sensing Change Detection | AC: 3835
Beyond Categorical Matching: Intra-Class Graded Relevance Estimation for Cross-Modal 3D Retrieval | AC: 5096
Beyond Common Sense: Grounding Logical Anomaly Detection in Inspection Criteria | AC: 4468
Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation | AC: 3187
Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents | AC: 4331
Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation | AC: 4913
Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives | AC: 3394
Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Re-rendering | AC: 3874
Beyond Isolated Scans: Cross-Phase Alignment of Structure and Topology for 3D Medical Pretraining | AC: 5629
Beyond Pixel Mimicry: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation | arXiv: 2606.23950 | AC: 5173
Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation | AC: 5497
Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR | AC: 5594
BeyondSight: Object Permanence for End-to-End Autonomous Driving | AC: 5981
BiCE-HG: A Bi-Conditional Egocentric Hand Gesture Dataset for Intelligent Reality Systems | AC: 5982
BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming | arXiv: 2606.24740 | AC: 5202
BioMTBee: Biologically Constrained Multi-View Template-Based 3D Reconstruction of Bumblebee | AC: 5834
BitRIC: Efficient Neural Compression of LiDAR Range Images via Hierarchical Bitplanes | AC: 5317
Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding | AC: 3141
BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion | AC: 5591
Boba: Batched Simulation for Physics-Based Gaussian Digital Twins | AC: 4947
Boosting 3D Foundation Models with Featureless Pose Optimization | arXiv: 2607.00579 | AC: 4837
Boosting 6D Object Pose Estimation via Monocular Depth Cues | AC: 5757
Boosting Correspondence Learning with Structure-Aware Estimator | AC: 4879
Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation | AC: 4230
Bootstrapping Articulated 3D Reconstruction from 2D Image Collections | AC: 5953
Bottom-up modeling of repeated elements via single image analysis-by-synthesis | AC: 3696
Bounding-Box Trajectories Matter for Video Anomaly Detection | AC: 5841
BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure | arXiv: 2607.00573 | AC: 4762
BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis | arXiv: 2606.29200 | AC: 5246
Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection | AC: 5691
BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning | AC: 4696
BrepLLM: Enabling Large Language Models to Understand Boundary Representations | arXiv: 2512.16413 | AC: 5778
Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs | AC: 5356
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction | arXiv: 2606.29445 | AC: 5028
BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment | AC: 4196
C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillation | AC: 4362
C3-Bench: A Context-Aware Change Captioning Benchmark | arXiv: 2606.25445 | AC: 3688
CabinSI: Omni-Cabin Spatial Reasoning through Explicit Visual Cognitive Maps | AC: 3315
Cambrian-P: Pose-Grounded Video Understanding | AC: 4080
Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting | arXiv: 2606.26754 | AC: 4306
CaPCL: Caption-Preserved Continual Learning for Text-to-Image Retrieval | AC: 5212
Caption Bottleneck Models | AC: 5814
Capturing Spectral and Spatial Patterns for Federated Remote Sensing Segmentation | AC: 5810
CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models | AC: 4809
CaRe: Critical Parameter Rectification for Efficient Visual Modeling | AC: 5148
CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion | AC: 5264
Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning | AC: 5072
Causal Yet Future-Aware: Dual-Path Temporal Modeling for Online Action Segmentation | AC: 5567
CausalDrive: Real-time Causal World Models for Autonomous Driving | AC: 3753
CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation | AC: 5969
CerDETR: Cell-Prior Empowered DETR for Cervical Lesion Detection | AC: 3977
CGCE: Classifier-Guided Concept Erasure in Generative Models | AC: 4668
Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens | AC: 4447
ChronoFlow Policy: Unifying Past-Future Interaction Flow in Visuomotor Policy Learning | AC: 3245
ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models | AC: 4007
CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains | AC: 5941
Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding | AC: 4463
CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection | AC: 3905
CL4D: Contrastive Language–4D Pretraining for Vision-Language Reasoning in Dynamic Scenes | AC: 4532
ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement | AC: 3992
CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition | AC: 5438
CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery | AC: 3386
Clue Matters: Empower Video Reasoning with Brain-Inspired Latent Clue Learning | AC: 4320
CLUE-VAD: Structured Semantic Clues for Understanding Explainable Events in Video Anomaly Detection | AC: 4744
ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation | AC: 3740
CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection | arXiv: 2606.20300 | AC: 3629
CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization | AC: 5960
CoDePose: Multi-View 3D Human Pose Estimation via Coupled 2D-3D Denoising Diffusion | AC: 5550
CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion | arXiv: 2606.30030 | AC: 3247
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts | AC: 4776
CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models | AC: 3708
Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning | AC: 3558
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models | AC: 5394
ComplexMimic: Human–Scene Interaction Imitation in Complex 3D Environments | AC: 3457
Comprehensive language–image pre-training for 3D medical image understanding | AC: 5833
Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs | AC: 4499
Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation | AC: 4207
Condensing Large-Scale Datasets Directly with Minimal Information Loss | arXiv: 2607.00916 | AC: 5756
ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation | AC: 3892
ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning | AC: 4462
Consistent Video-to-Video Translation via Explicit Correspondences | AC: 3572
Constrained Rotation Optimization: Revisiting Crop-Based Gaze Estimation | AC: 4912
Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification | AC: 4764
Continuous Speculative Decoding for Autoregressive Image Generation | arXiv: 2411.11925 | AC: 5776
ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control | AC: 3535
Control-DINO: Feature Space Conditioning for Controllable Video Diffusion | AC: 4902
ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering | AC: 5370
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints | arXiv: 2603.11755 | AC: 3544
Controlling Motion Transfer in Diffusion Transformers via Attention Heads | AC: 3621
Conversational Human Audio-visual Talking Dialogue Generation | AC: 4941
CooperScene: Multi-Modal Cooperative Autonomy Benchmark with C-V2X Communication Characterization | arXiv: 2606.31219 | AC: 4574
CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection | arXiv: 2510.14792 | AC: 3265
CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning | AC: 5196
CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport | AC: 5259
CRD-Net: Frequency-Adaptive Feature Injection and Change Decoupling for Building Damage Assessment | AC: 5684
CTEPM: Continuous-Time Event Process Memory for Long-Video Language Models | AC: 5848
CulinaryCut: A Physics-aware Vision-Language-Action Benchmark for Food Cutting via Material Point Method | AC: 5439
CURE: Cumulative Knowledge Reuse for Efficient Device-Server Hybrid Inference in Vision-Language Models | AC: 5036
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning | arXiv: 2606.22394 | AC: 5545
Curvature-Guided Mixing for MLLM Adaptation | arXiv: 2606.24963 | AC: 5041
CUST : Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution | AC: 4220
CustomX: Unified Character, Action, and Scene Customization in Video World Models | arXiv: 2512.17796 | AC: 4020
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency | AC: 5343
DARL: Efficient Document-to-Markup Generation via Look-Ahead Diffusion Trajectory Sampling | AC: 5755
DART: Deformable Adaptive Reasoning with Temporal Queries for Online Skeleton-Based Action Recognition | AC: 3850
DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression | AC: 4843
Data Circuit Breaker: Identifying Training, Test, and Generated Data in Image Generative Models | arXiv: 2606.23872 | AC: 3593
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space | AC: 4727
DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation | AC: 4282
DE2TR: Dual Evidence Detection Transformer for Video Temporal Grounding | AC: 5412
Decoding Multimodal Causality: End-to-End Multimodal Mediation Pathways Inference | AC: 3479
DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection | AC: 4729
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces | arXiv: 2603.14354 | AC: 4059
DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering | arXiv: 2602.19323 | AC: 4267
Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models | AC: 4930
DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking | AC: 3443
Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation | arXiv: 2512.20117 | AC: 4151
Denoised Variance-Based Pruning with Optimal Brain Bias Compensation | AC: 3650
Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging | AC: 3316
Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation | arXiv: 2606.21956 | AC: 5434
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views | arXiv: 2606.23557 | AC: 5231
Dense Video Understanding with Inter-tokenization Acceleration | AC: 3614
Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision | AC: 5101
DepWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors | arXiv: 2607.00889 | AC: 3937
DeRA: Decoupled Representation Alignment for Video Tokenization | AC: 3946
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models | AC: 3456
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams | AC: 3381
DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues | arXiv: 2606.26602 | AC: 4297
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models | AC: 3667
Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution | arXiv: 2606.22314 | AC: 5647
Diffusion-Based Material Regularization for Physics-Based Inverse Rendering | arXiv: 2606.31065 | AC: 3441
DiNBV-Grasp: Real-Time Distance-Aware Two-Stage Next-Best-View for Robotic Grasping | AC: 4360
DisentangledTMR: Privacy-Preserving Skeleton Motion Retargeting via Factorized Transformers | AC: 5993
Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning | arXiv: 2606.25488 | AC: 4400
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation | arXiv: 2606.20196 | AC: 3773
DIVA: Instruction-Aware Vision Token Pruning via Dual-Probe Attention Discrepancy | AC: 4758
DiverseAD: A Large-Scale Driving Dataset with Diverse Atmospheric Conditions | AC: 4645
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models | arXiv: 2605.01896 | AC: 5089
DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming | arXiv: 2606.28840 | AC: 4664
DnA: Denoising Attention for Visual Tasks | AC: 3828
DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction | AC: 4405
Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data | AC: 5440
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts | arXiv: 2607.00666 | AC: 4444
Don’t Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance | arXiv: 2606.27371 | AC: 3156
Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement | AC: 4878
DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery | AC: 4517
Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off | arXiv: 2603.22607 | AC: 4939
DriftScope: Measuring The Hidden Effects of Diffusion Model Fine-Tuning | arXiv: 2607.00183 | AC: 3510
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout | arXiv: 2605.05092 | AC: 3775
DriveVA: Video Action Models are Zero-Shot Drivers | arXiv: 2604.04198 | AC: 3252
DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation | arXiv: 2606.31918 | AC: 3336
DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution | arXiv: 2606.29198 | AC: 5665
Dual-End Consistency Model | arXiv: 2602.10764 | AC: 5288
Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution | arXiv: 2606.26716 | AC: 3760
Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition | AC: 5513
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation | arXiv: 2606.27268 | AC: 4867
E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes | arXiv: 2604.04834 | AC: 4840
EAGS: Error-Aware Gaussian Splatting with Dual-Confidence-Guided Modeling for Uncalibrated Driving Scenes | AC: 4526
EatVid-Bench: A Multimodal Fine-Grained Eating Behavior Video Dataset | AC: 5037
ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation | AC: 3709
EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics | AC: 3747
Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing | arXiv: 2603.03143 | AC: 3702
Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT–Quantization Embedding | arXiv: 2606.22285 | AC: 5506
Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion | arXiv: 2606.30215 | AC: 4023
Egocentric Procedure Parsing | AC: 4540
EgoEverything: A Benchmark for Human Behavior–Inspired Long-Context Egocentric Video Understanding in AR Environment | AC: 4529
EgoExo-Con: Exploring View-Invariant Video Temporal Understanding | arXiv: 2510.26113 | AC: 3203
EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage | AC: 3471
EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding | arXiv: 2606.24422 | AC: 4403
EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning | arXiv: 2511.18242 | AC: 4523
ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval | arXiv: 2606.20280 | AC: 5615
Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding | AC: 3478
Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings | AC: 3466
EMOTE: Expressive Motion and Shape Disentanglement for Human Animation | arXiv: 2606.28026 | AC: 3741
EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models | AC: 4214
Enhancing Embodied Reasoning and Grounding by Novel View Synthesis | AC: 4036
Entropy-Controlled Flow Matching | arXiv: 2602.22265 | AC: 3810
EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal | arXiv: 2512.21545 | AC: 5267
ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis | arXiv: 2603.25168 | AC: 5878
Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs | arXiv: 2606.20177 | AC: 3870
Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations | arXiv: 2606.24716 | AC: 5939
Event-Driven Video Generation | arXiv: 2603.13402 | AC: 5108
Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks | arXiv: 2603.11689 | AC: 5715
Exploiting Local Flatness for Efficient Out-of-Distribution Detection | arXiv: 2606.29952 | AC: 5630
Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation | AC: 5803
ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling | arXiv: 2606.31201 | AC: 5992
ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving | arXiv: 2604.02714 | AC: 5991
Exploring Efficient Reasoning Segmentation with Small Language Models | AC: 4052
Fabric Image Demoiréing Benchmark from Synthesis to Restoration | arXiv: 2606.24072 | AC: 3616
Face Anything: 4D Face Reconstruction from Any Image Sequence | arXiv: 2604.19702 | AC: 4482
FaceMoE: Mixture of Experts for Low-Resolution Face Recognition | arXiv: 2606.32040 | AC: 3339
FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis | AC: 5679
FD²: A Dedicated Framework for Fine-Grained Dataset Distillation | arXiv: 2603.25144 | AC: 3742
FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration | arXiv: 2606.28654 | AC: 3206
FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs | arXiv: 2606.22875 | AC: 3888
FeVOS: Foresight Expression Video Object Segmentation | arXiv: 2606.25585 | AC: 5598
Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples | arXiv: 2509.25682 | AC: 5926
Fidelity- and Perception-Aware Local Implicit Attention for Arbitrary-Scale Image Super-Resolution | arXiv: 2606.21910 | AC: 3972
Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion | arXiv: 2412.02798 | AC: 3834
Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning | AC: 4485
FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control | AC: 4328
FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction | arXiv: 2606.21373 | AC: 4753
FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation | arXiv: 2606.22424 | AC: 4005
FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation | arXiv: 2511.21029 | AC: 4239
FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring | arXiv: 2512.04390 | AC: 5366
Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE | arXiv: 2606.26938 | AC: 3647
Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection | arXiv: 2606.22378 | AC: 5799
FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution | arXiv: 2606.28745 | AC: 4909
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting | AC: 4354
From Gaze to Meaning: An AI Agent for Unified Zero-Shot Grounding and Explanation | AC: 5517
From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP | arXiv: 2606.26535 | AC: 3720
From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs | arXiv: 2606.29461 | AC: 3547
From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation | arXiv: 2606.23486 | AC: 5450
FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model | arXiv: 2606.20110 | AC: 3978
FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal | arXiv: 2603.19036 | AC: 4886
G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation | arXiv: 2601.03510 | AC: 5646
GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models | arXiv: 2601.18197 | AC: 5058
Gaussian Belief Propagation Network for Depth Completion | arXiv: 2601.21291 | AC: 3367
GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation | arXiv: 2603.26661 | AC: 4503
GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine | AC: 5462
GEM: Generative Supervision Helps Embodied Intelligence | AC: 3349
Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition | arXiv: 2606.22416 | AC: 3293
GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence | arXiv: 2511.21945 | AC: 3508
Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval | arXiv: 2602.00813 | AC: 4117
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding | AC: 3262
Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior | arXiv: 2606.31814 | AC: 4869
GenSP: Consistent Spherical Parameterization via Learning Shape Generative Models | arXiv: 2607.00492 | AC: 3856
Geo-ID: Test-Time Geometric Consensus for Cross-View Consistent Intrinsics | arXiv: 2603.13859 | AC: 3513
GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Traces | AC: 3259
GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising | arXiv: 2606.30003 | AC: 4817
Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning | arXiv: 2606.26973 | AC: 3557
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning | arXiv: 2606.25347 | AC: 4569
Geometry-Aware Style Transfer in 3D Gaussian Splatting | arXiv: 2606.24144 | AC: 4174
Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration | arXiv: 2606.20103 | AC: 4656
GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis | arXiv: 2603.14965 | AC: 3876
GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation | AC: 3217
GKDT: General Keypoint Detection Transformer | arXiv: 2607.00752 | AC: 3679
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing | AC: 3375
GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction | arXiv: 2604.19624 | AC: 3270
Graph Coloring for Multi-Task Learning | arXiv: 2509.16959 | AC: 3425
Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field | AC: 3490
GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition | arXiv: 2602.03370 | AC: 3955
GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation | arXiv: 2603.26266 | AC: 3244
Guiding the Blind: Generalizing GUI Agents to Unseen Websites via Multimodal Tutorials | AC: 4245
H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks | arXiv: 2606.25578 | AC: 5686
HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving | AC: 3249
HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration | arXiv: 2606.28215 | AC: 5188
HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking | arXiv: 2607.00494 | AC: 4786
Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation | arXiv: 2606.31071 | AC: 5648
Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation | arXiv: 2606.24296 | AC: 5612
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training | arXiv: 2606.20189 | AC: 3430
HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning | AC: 5381
Histogram-constrained Image Generation | arXiv: 2606.31683 | AC: 4232
Histopathology Multi-modal Embedding for Pathology Composed Retrieval | arXiv: 2502.07221 | AC: 5623
Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving | arXiv: 2606.31096 | AC: 5928
HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding | arXiv: 2602.12957 | AC: 5282
HSDF-Lane: Height-Aligned Signed Distance Field with Semantic Lane Prior for 3D Lane Detection | arXiv: 2606.31172 | AC: 5119
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human–Scene Interactions | AC: 3313
HuCollisionField: Resolving Self-Collisions via Neural Fields for Human Prediction | arXiv: 2606.29686 | AC: 3864
Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum | AC: 3751
Hybrid Event–Frame Sensors: Modeling, Calibration, and Simulation | arXiv: 2511.18037 | AC: 3755
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding | arXiv: 2607.00428 | AC: 5643
HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization | arXiv: 2604.20328 | AC: 5084
Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting | arXiv: 2607.00159 | AC: 5899
Image Warping for Image-to-Image Translation | arXiv: 2606.31018 | AC: 5130
Improving Adversarial Robustness via Activation Amplification and Attenuation | arXiv: 2606.27784 | AC: 3522
Improving Sparse-View 3DGS Generalization via Flat Minima Optimization | arXiv: 2607.00885 | AC: 5368
In-context Region-based Drag: Drag Any Region to Any Shape | arXiv: 2606.25907 | AC: 3552
Information-Regularized Attention for Visual-Centric Reasoning | arXiv: 2607.00434 | AC: 5530
Interact3D: Compositional 3D Generation of Interactive Objects | arXiv: 2603.16085 | AC: 3861
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars | AC: 3402
InterEdit: Navigating Text-Guided Multi-Human 3D Motion Editing | arXiv: 2603.13082 | AC: 3603
Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment | arXiv: 2606.30262 | AC: 5537
Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization | arXiv: 2606.31695 | AC: 4371
IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation | arXiv: 2606.29880 | AC: 4120
ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation | arXiv: 2505.20935 | AC: 5373
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising | arXiv: 2606.20563 | AC: 4414
KATANA: Knowledge-Aligned Topology-Aware Neural Agents for RL-Driven Vision-Language Model Compression | AC: 5897
Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding | AC: 5468
Kirin: Animal Motion Generation from In-the-Wild Video | AC: 3829
Knowledge-Centric Agents for Workflow Generation in ComfyUI | AC: 4258
LaGen: Towards Autoregressive LiDAR Scene Generation | arXiv: 2511.21256 | AC: 4888
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures | arXiv: 2605.04035 | AC: 3643
Latent Visual Diffusion Reasoning with Monte Carlo Tree Search | arXiv: 2606.27988 | AC: 3822
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion | arXiv: 2603.14526 | AC: 3581
Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking | arXiv: 2509.12046 | AC: 3209
LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection | arXiv: 2512.05663 | AC: 3882
Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models | arXiv: 2403.19645 | AC: 3264
Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision | AC: 3825
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents | arXiv: 2606.31270 | AC: 5478
Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding | AC: 4771
Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval | arXiv: 2607.00374 | AC: 4892
Learning to Deny: Action Denial in Multimodal Large Language Models | arXiv: 2606.31187 | AC: 3915
Learning Transferable Dynamics Priors from Action to World Modeling | arXiv: 2606.29501 | AC: 3656
Learning Video Dynamics with Predictive Differentiable Rendering | arXiv: 2606.31050 | AC: 4642
LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models | arXiv: 2606.23686 | AC: 4895
LibraGen: Playing a Balance Game in Subject-Driven Video Generation | AC: 3221
LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement | arXiv: 2606.23539 | AC: 4839
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing | arXiv: 2606.26740 | AC: 4792
LogicIR: Logic Gate Networks for Image Restoration | arXiv: 2606.26609 | AC: 3151
LogiCo: A Unified Framework for Logical and Structural Anomaly Detection | arXiv: 2606.28688 | AC: 3604
Long-term Traffic Simulation via Structured Autoregressive Modeling | arXiv: 2606.31209 | AC: 5085
Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition | arXiv: 2607.00090 | AC: 3660
LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation | arXiv: 2509.17773 | AC: 3999
LUNA: Learning Universal 3D Human Animation Beyond Skinning | arXiv: 2606.31981 | AC: 4925
M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection | arXiv: 2505.10931 | AC: 3158
Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs | arXiv: 2602.05275 | AC: 5057
MambaRaw: Selective State Space Modeling for Efficient 4K RAW Image Reconstruction | arXiv: 2606.24479 | AC: 3408
MASS: Motion-Aligned Selective Scan for Flow-Based Video Frame Interpolation | arXiv: 2606.27718 | AC: 3303
Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras | arXiv: 2604.18744 | AC: 4933
MATCH: Flow Matching for Multi-View Anomaly Detection | arXiv: 2606.24375 | AC: 4872
Matryoshka Gaussian Splatting | AC: 3234
MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction | arXiv: 2604.01958 | AC: 4385
MedCAGD: Context-Aware Gated Decoder for Robust Medical Image Segmentation | arXiv: 2607.00409 | AC: 4399
MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing | arXiv: 2606.23455 | AC: 3980
MemLearner: Learning to Query Context Memory for Video World Models | arXiv: 2606.31734 | AC: 3900
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization | arXiv: 2607.00902 | AC: 4624
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation | arXiv: 2606.26016 | AC: 3631
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations | arXiv: 2606.27779 | AC: 3789
MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein | arXiv: 2606.29462 | AC: 4670
MirrorPPR: Exemplar-Based Portrait Photo Retouching | arXiv: 2606.29308 | AC: 5694
MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation | arXiv: 2606.28142 | AC: 4612
MLVC: A Multi-platform Learned Video Codec for Real-World Deployment | arXiv: 2606.28027 | AC: 4404
MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation | arXiv: 2604.19679 | AC: 3470
MobileManiBench: Simplifying Model Verification for Mobile Manipulation | arXiv: 2602.05233 | AC: 4029
ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation | arXiv: 2604.07021 | AC: 4138
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance | AC: 4484
Moiré Video Authentication: A Physical Signature Against AI Video Generation | arXiv: 2604.01654 | AC: 3761
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web | AC: 4684
Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading | arXiv: 2606.28144 | AC: 5324
MonoSR: Open-Vocabulary Spatial Reasoning on Monocular Images | arXiv: 2511.19119 | AC: 4275
Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting | arXiv: 2606.30017 | AC: 3145
MotionAtlas: A High-Quality Dataset and Benchmark for Dense Motion Captioning | arXiv: 2606.29531 | AC: 4897
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment | arXiv: 2607.00858 | AC: 5408
Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction | arXiv: 2606.26812 | AC: 3254
Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments | arXiv: 2607.00457 | AC: 5948
Multi-scale Object-Aware Gaze Estimation via Geometric Reasoning | arXiv: 2606.29334 | AC: 3804
Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts | arXiv: 2607.00371 | AC: 5141
Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation | arXiv: 2606.22197 | AC: 3218
MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving | AC: 5547
NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation | arXiv: 2606.29395 | AC: 4846
NavWM: A Unified Navigation World Model for Foresight-Driven Planning | arXiv: 2606.24101 | AC: 3973
NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models | arXiv: 2606.22537 | AC: 3940
Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating | arXiv: 2603.12598 | AC: 4147
Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors | arXiv: 2603.15129 | AC: 3536
Nexus-Vid: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models | arXiv: 2605.31603 | AC: 5094
NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling | arXiv: 2606.23200 | AC: 4200
No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs | arXiv: 2606.31933 | AC: 5290
NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment | arXiv: 2606.18066 | AC: 3859
Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold | arXiv: 2607.00647 | AC: 4934
NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics | arXiv: 2606.31764 | AC: 4225
Obliviate: Erasing Concepts from Autoregressive Image Generation Models | arXiv: 2606.28643 | AC: 4923
OCTOPUS: Multi‑Agentic Universal Compositional Visual Retrieval | AC: 5802
Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion | arXiv: 2606.21135 | AC: 3176
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning | AC: 3376
OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data | AC: 4238
OmniNWM: Unifying the State-Action-Reward Triad for Closed-Loop Panoramic Driving Navigation World Models | arXiv: 2510.18313 | AC: 3205
OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning | AC: 3451
OmniX: Any-view and Any-time 4D reconstruction via Feed-forward Trajectory Fields | AC: 3323
On Test-Time Scaling for Vision-Language Models | arXiv: 2606.28864 | AC: 4216
On the Faithfulness of Post-Hoc Concept Bottleneck Models | arXiv: 2606.30498 | AC: 5447
On the Vulnerability of Parameter-Level Defenses to Model Merging | arXiv: 2606.30360 | AC: 3680
One Video, One World: Turning Monocular Video into Physical 4D Scenes | arXiv: 2606.31388 | AC: 3356
OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal Action Localization | arXiv: 2607.00289 | AC: 3903
OP3DSG: Open-vocabulary Part-aware 3D Scene Graph Generation for Real-world Environments | arXiv: 2606.29786 | AC: 4307
Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints | arXiv: 2606.24353 | AC: 3266
OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos | arXiv: 2606.25245 | AC: 4440
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models | arXiv: 2606.31026 | AC: 5040
P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling | AC: 5238
PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates | arXiv: 2512.06845 | AC: 4682
Pano3D: Unified 3D Reconstruction and Panoptic Segmentation | arXiv: 2606.14307 | AC: 4920
PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding | arXiv: 2512.20907 | AC: 4323
Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models | arXiv: 2606.27373 | AC: 4470
Perceptual Projection Pruning: Diversity-Aware Video Token Pruning for Multimodal Large Language Models | AC: 5817
Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising | arXiv: 2607.00407 | AC: 5977
Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer | arXiv: 2511.19778 | AC: 4089
PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models | AC: 3450
PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing | arXiv: 2606.26551 | AC: 5047
PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation | arXiv: 2512.24551 | AC: 4063
Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch | arXiv: 2604.09100 | AC: 4773
Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation | arXiv: 2606.25306 | AC: 5501
PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation | arXiv: 2606.26916 | AC: 5129
PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling | arXiv: 2606.21162 | AC: 4193
PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation | AC: 3174
PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection | arXiv: 2507.02393 | AC: 4690
Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision | arXiv: 2606.29301 | AC: 3855
PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models | arXiv: 2606.22540 | AC: 3170
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation | arXiv: 2606.29908 | AC: 5211
Pose Anything Anywhere: Model-free Object Poses from Arbitrary References | arXiv: 2606.23634 | AC: 4278
Prevention over Correction: Learning Aligned Representations in One-shot Federated Learning | AC: 4293
PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving | arXiv: 2606.31830 | AC: 4451
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models | arXiv: 2603.19466 | AC: 4434
Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video | arXiv: 2607.00157 | AC: 4740
Prompt2Effect: Training-Free LoRA Synthesis for Controllable Video Effects | arXiv: 2606.13971 | AC: 3453
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering | AC: 5675
ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs | arXiv: 2605.01971 | AC: 5957
PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking | arXiv: 2606.30476 | AC: 3664
RAGA: Real Time Ray Traced Gaussian Shadow Casting for 3DGS Avatar-Scene Interaction | arXiv: 2606.29329 | AC: 3220
Rank-Aware Hyperbolic Alignment for Vision–Language Dataset Distillation | arXiv: 2606.29464 | AC: 4352
RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation | arXiv: 2606.22749 | AC: 5166
RBE-Flow:Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration | arXiv: 2606.30492 | AC: 4906
Real-Time Source-Free Object Detection | arXiv: 2606.31834 | AC: 4975
RefAlign: Representation Alignment for Reference-to-Video Generation | arXiv: 2603.25743 | AC: 3790
Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation | arXiv: 2506.23102 | AC: 5301
Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning | AC: 3298
Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering | arXiv: 2505.17338 | AC: 4144
RePer-360: Releasing Perspective Priors for 360° Depth Estimation via Self-Modulation | arXiv: 2603.05999 | AC: 3917
Repurposing Geometric Foundation Models for Multi-view Diffusion | AC: 3136
ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision–Language Models | arXiv: 2607.00361 | AC: 5876
Residual-Guided Expert Specialization for Incomplete Multimodal Learning | arXiv: 2606.30355 | AC: 3678
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration | arXiv: 2606.26769 | AC: 4157
RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception | arXiv: 2606.31895 | AC: 4555
Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions | arXiv: 2605.24251 | AC: 3516
Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise | arXiv: 2511.18775 | AC: 4096
Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection | arXiv: 2606.23069 | AC: 5171
Rethinking Training and Inference for Trajectory Forecasting: Linking Winner-Take-All back to GMMs | arXiv: 2606.26424 | AC: 4060
Revisiting Autoregressive Models for Generative Image Classification | arXiv: 2603.19122 | AC: 3984
Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need | AC: 3431
Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation | arXiv: 2606.31382 | AC: 4854
RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios | arXiv: 2511.18011 | AC: 5365
Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors | arXiv: 2606.29428 | AC: 5411
RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning | arXiv: 2606.28266 | AC: 3916
S2-FracMix: Self-Saliency Fractal Mixup | arXiv: 2606.25784 | AC: 3462
SALT: Self-Consistent Distribution Matching with Cache-Aware Training for Few-Step Video Generation | arXiv: 2604.03118 | AC: 3473
SAM2Matting: Generalized Image and Video Matting | arXiv: 2606.27339 | AC: 4966
SARIF: Segment Anything for Robust Image Forensics | arXiv: 2606.21108 | AC: 5314
ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision–Language Models | arXiv: 2606.29579 | AC: 4961
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation | arXiv: 2606.30124 | AC: 5783
See & Sniff: Learning Visuo-Olfactory Representations | arXiv: 2606.27307 | AC: 4376
Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation | arXiv: 2606.29941 | AC: 4435
Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation | AC: 3331
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing | arXiv: 2607.00124 | AC: 5741
Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning | AC: 5852
Self-supervised Garment Dynamics with Persistent Wrinkles | arXiv: 2606.25065 | AC: 3705
Semantic Browsing: Controllable Diversity for Image Generation | arXiv: 2606.23679 | AC: 4450
SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models | arXiv: 2606.27444 | AC: 4801
SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Tracking | arXiv: 2606.24449 | AC: 4693
SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions | arXiv: 2607.00369 | AC: 4723
ShellMaker: Language-Guided Exterior Completion under Structural Constraints | arXiv: 2606.31680 | AC: 3519
SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset | arXiv: 2606.30001 | AC: 4963
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models | arXiv: 2606.27741 | AC: 5178
SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning | arXiv: 2506.07460 | AC: 4313
SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation | arXiv: 2606.28626 | AC: 4999
SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks | arXiv: 2606.24361 | AC: 3533
Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs | arXiv: 2604.20937 | AC: 5652
SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation | arXiv: 2603.14152 | AC: 3548
SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery | arXiv: 2511.20157 | AC: 3845
SkelEM: Explicit Decoupling of Topology and Details for Self-supervised Axial Super-Resolution in Volume Microscopy | arXiv: 2606.30012 | AC: 4327
Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models | arXiv: 2511.14900 | AC: 4291
SlowBA: An efficiency backdoor attack towards VLM-based GUI agents | arXiv: 2603.08316 | AC: 5078
SMART: When is it Actually Worth Expanding a Speculative Tree? | arXiv: 2604.09731 | AC: 4155
Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective | arXiv: 2512.10244 | AC: 4085
SONIC: Spectral Optimization of Noise for Inpainting with Consistency | arXiv: 2511.19985 | AC: 5954
Spanning the Visual Analogy Space with a Weight Basis of LoRAs | arXiv: 2602.15727 | AC: 4237
Sparsity-Inducing Divergence Losses for Biometric Verification | arXiv: 2606.31664 | AC: 5481
SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning | AC: 5289
SPEAR: A Simulator for Photorealistic Embodied AI Research | AC: 3273
SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation | arXiv: 2607.00525 | AC: 5880
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution | arXiv: 2603.06275 | AC: 5583
Spectral Evolution-Guided Token Pruning in Large Multimodal Models | arXiv: 2606.24165 | AC: 3609
Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations | arXiv: 2606.23129 | AC: 4373
SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision | arXiv: 2603.24036 | AC: 3727
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models | arXiv: 2510.12784 | AC: 4190
StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production–Living Simulations with Stardew Valley | arXiv: 2507.07445 | AC: 5361
Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging | AC: 4368
Staying VIGILant: Mitigating Visual Laziness in MLLMs via Information-Theoretic Alignment | arXiv: 2606.26387 | AC: 4110
Steerable Vision Transformers | arXiv: 2604.02327 | AC: 5945
Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance | arXiv: 2506.20995 | AC: 4191
StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors | arXiv: 2606.30545 | AC: 3379
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning | arXiv: 2607.00465 | AC: 5503
StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation | arXiv: 2605.21466 | AC: 3345
Streaming Dense Voxel Representations for 3D Occupancy Prediction | arXiv: 2503.22087 | AC: 3241
Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space | arXiv: 2606.21705 | AC: 4066
Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers | arXiv: 2606.22383 | AC: 5700
Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding | arXiv: 2604.07753 | AC: 5319
Syn4D: A Multiview Synthetic 4D Dataset | AC: 3248
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation | arXiv: 2606.30849 | AC: 3830
Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction | arXiv: 2510.03117 | AC: 3459
TaskTok: Delving into Task Tokens for Task-driven Image Restoration | arXiv: 2606.26615 | AC: 3148
TaxoMIL: Taxonomy-Constrained Learning for Hierarchical Whole Slide Image Analysis | arXiv: 2606.31100 | AC: 5220
Tesselating The Earth | arXiv: 2606.27514 | AC: 5452
Test Time Training for Long Videos via Frame Forgetting Network | arXiv: 2606.26515 | AC: 4271
Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Generation | arXiv: 2606.22726 | AC: 5082
Text-Conditioned Background Generation for Editable Multi-Layer Documents | arXiv: 2512.17151 | AC: 3585
TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts | arXiv: 2606.28077 | AC: 4871
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models | arXiv: 2607.00402 | AC: 5377
The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning | arXiv: 2606.30875 | AC: 3333
There and Back Again: A Flexible-Frame Transformer for Multi-Exposure Fusion | arXiv: 2606.27905 | AC: 5062
Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs | arXiv: 2606.31471 | AC: 5278
TIIF-Bench: How Does Your T2I Model Follow Your Instructions? | AC: 3177
TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration | AC: 5122
TORA: Topological Representation Alignment for 3D Shape Assembly | arXiv: 2604.04050 | AC: 3567
Toward Robust In-Context Segmentation via Concept Guidance | arXiv: 2606.28149 | AC: 5254
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning | arXiv: 2511.20196 | AC: 4358
Towards Consistent and Efficient Dataset Distillation via Diffusion-Driven Selection | AC: 5321
Towards Generalizable Robotic Manipulation in Dynamic Environments | arXiv: 2603.15620 | AC: 3319
Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation | arXiv: 2606.30598 | AC: 3943
Towards Interactive Global Geolocation Assistant | AC: 3263
Towards Long-Form Spatio-Temporal Video Grounding | arXiv: 2602.23294 | AC: 4321
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption | AC: 4508
Towards Metric-Agnostic Trajectory Forecasting | arXiv: 2607.01133 | AC: 5818
Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics | arXiv: 2512.13660 | AC: 3404
Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching | AC: 5609
Training-Free Refinement of Flow Matching with Divergence-based Sampling | AC: 3225
Transferability Between Understanding and Generation in Unified Multimodal Models | AC: 3137
Triangular Consistency as a Universal Constraint for Learning Optical Flow | arXiv: 2606.19938 | AC: 3812
TriMotion: Modality-Agnostic Camera Control for Video Generation | AC: 3398
Trustworthy Image Authentication using Forensic Knowledge Graphs | arXiv: 2606.23917 | AC: 3521
UEval: A Benchmark for Unified Multimodal Generation | AC: 3346
UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables | arXiv: 2606.31242 | AC: 5384
Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics | arXiv: 2606.27554 | AC: 3563
UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving | arXiv: 2601.04453 | AC: 4081
UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation | arXiv: 2603.22282 | AC: 3405
UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | arXiv: 2512.21078 | AC: 4134
UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation | arXiv: 2606.31451 | AC: 5005
UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving | arXiv: 2606.25736 | AC: 4186
UniTranslator: A Unified Multi-modal framework for End-to-end In-Image Machine Translation | arXiv: 2606.24333 | AC: 4127
UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras | arXiv: 2606.29794 | AC: 4818
Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection | arXiv: 2602.14679 | AC: 3278
Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings | arXiv: 2606.30777 | AC: 5485
URoPE: Universal Relative Position Embedding across Geometric Spaces | arXiv: 2604.18747 | AC: 5575
VCBench: A Streaming Counting Benchmark for Spatial-Temporal State Maintenance in Long Videos | arXiv: 2603.12703 | AC: 3399
Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization | arXiv: 2605.11913 | AC: 5518
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously | AC: 3229
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement | arXiv: 2607.00446 | AC: 5813
ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models | AC: 3165
ViewSplat: View-Adaptive Dynamic Gaussian Splatting for Feed-Forward Synthesis | arXiv: 2603.25265 | AC: 3759
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution | arXiv: 2606.27313 | AC: 5257
VisCritic: Visual State Comparison as Process Reward for GUI Agents | arXiv: 2606.24525 | AC: 4958
Vision Bridge Transformer at Scale | AC: 3232
VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning | arXiv: 2603.01195 | AC: 4167
VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context | arXiv: 2606.30288 | AC: 5979
Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers | arXiv: 2607.00382 | AC: 3543
VLA Knows Its Limits | arXiv: 2602.21445 | AC: 4137
VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors | arXiv: 2510.00458 | AC: 3853
VOCA: Visual Odometry with Codec Awareness | arXiv: 2607.00189 | AC: 3509
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction | arXiv: 2509.19297 | AC: 3169
VTEdit-Bench: A Comprehensive Benchmark for Multi-Reference Image Editing Models in Virtual Try-On | arXiv: 2603.11734 | AC: 3764
WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching | AC: 3393
Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs | arXiv: 2607.00302 | AC: 5669
Walking in the Implicit: Interactive World Exploration via Neural Scene Representation | arXiv: 2606.30045 | AC: 3302
WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation | AC: 5413
What if? Emulative Simulation with World Models for Situated Reasoning | arXiv: 2603.06445 | AC: 4721
When Sinks Help or Hurt: Unified Framework for Attention Sink in MLLMs | arXiv: 2604.03316 | AC: 3694
WorldAgents: Can Foundation Image Models be Agents for 3D World Models? | AC: 5821
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation | arXiv: 2606.30248 | AC: 5650
Zero-shot Depth from Defocus | arXiv: 2603.26658 | AC: 3798
Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models | arXiv: 2606.31456 | AC: 4509
ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting | AC: 3373
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory | AC: 3286
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding | AC: 3142
VOID: Video Object and Interaction Deletion | AC: 3342
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment | AC: 3197
FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry | AC: 3189
TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation | AC: 3139
Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training? | AC: 3320
XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexity | AC: 3426
S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight | AC: 3407
Human Mesh Modeling for Anny Body | AC: 3422
UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors | AC: 3418
RAU: Reference-based Anatomical Understanding with Vision-Language Models | AC: 3449
TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy | AC: 3423
Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution | AC: 3370
DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies | AC: 3382
CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing | AC: 3458
CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose | AC: 3600
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models | AC: 3559
FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting | AC: 3541
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction | AC: 3583
IRIS: Intersection-aware Ray-based Implicit Editable Scenes | AC: 3495
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments | AC: 3594
Query-Kontext: An Unified Multimodal Model for Image Generation and Editing | AC: 3482
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility | AC: 3472
SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving | AC: 3597
StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views | AC: 3486
Surprise Forcing: What to Remember, When to Skip in Long Video Generation | AC: 3534
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing | AC: 3530
Tri-Efficient Transfer Learning for Point Cloud Videos | AC: 3624
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward | AC: 3500
ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images | AC: 3574
VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations | AC: 3595
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning | AC: 3599
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model | AC: 3580
World Reconstruction From Inconsistent Views | AC: 3497
Scaling Laws for Black-box Adversarial Attacks | AC: 3565
ECHO: Ego-centric Modeling of Human-Object Interactions | AC: 3503
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space | AC: 3460
Shared LoRA Subspaces for almost Strict Continual Learning | AC: 3502
T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability | AC: 3505
TACO-Net: Topological Signatures Triumph in 3D Object Classification | AC: 3582
HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching | AC: 3494
NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control | AC: 3499
DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference | AC: 3584
Learning to Recover Task Experts from a Multi-Task Merged Model | AC: 3618
Masked Depth Modeling for Spatial Perception | AC: 3692
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery | AC: 3179
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling | AC: 3227
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding | AC: 3637
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution | AC: 3771
MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens | AC: 3215
RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing | AC: 3410
ReMoMask: Retrieval-Augmented Masked Motion Generation | AC: 3469
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models | AC: 3673
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising | AC: 3701
EvoVLA: Self-Evolving Vision-Language-Action Model | AC: 3353
DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation | AC: 3378
ReSplat: Learning Recurrent Gaussian Splatting | AC: 3147
DINO-SLAM: DINO-Informed RGB-D SLAM for Neural Implicit and Explicit Representations | AC: 3777
VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model | AC: 3788
SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning | AC: 3237
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams | AC: 3341
VersatileMotion: A Unified Framework for Motion Synthesis and Comprehension | AC: 3374
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting | AC: 3787
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion | AC: 3615
QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration | AC: 3655
GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing | AC: 3710
Egocentric World Model for Photorealistic Hand Object Interaction Synthesis | AC: 3737
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation | AC: 3171
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion | AC: 3212
MegaFlow: Zero-Shot Large Displacement Optical Flow | AC: 3344
Dual-Anchoring: Addressing State Drift in Vision-Language Navigation | AC: 3365
VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection | AC: 3258
MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction | AC: 3312
LlamaSeg: Image Segmentation via Autoregressive Mask Generation | AC: 3644
RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics | AC: 3802
Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs | AC: 3809
Make Geometry Matter for Spatial Reasoning | AC: 3231
ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA | AC: 3277
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion | AC: 3372
Learning to Generate Rigid Body Interactions with Video Diffusion Models | AC: 3697
Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation | AC: 3714
Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models | AC: 3721
VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization | AC: 3750
PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models | AC: 3768
Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents | AC: 3785
VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models | AC: 3824
Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs | AC: 3144
OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure | AC: 3150
Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models | AC: 3240
STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding | AC: 3272
Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation | AC: 3279
OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction | AC: 3290
RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes | AC: 3360
Auto3R: Automated 3D Reconstruction and Scanning via Data-driven Uncertainty Quantification | AC: 3391
LiFlow: Flow Matching for 3D LiDAR Scene Completion | AC: 3569
Multi-dimensional Preference Alignment by Conditioning Reward Itself | AC: 3625
InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization | AC: 3684
Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection | AC: 3698
SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification | AC: 3732
GimbalDiffusion: Gravity-Aware Camera Control for Video Generation | AC: 3735
MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos | AC: 3770
MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents | AC: 3784
R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation | AC: 3816
ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering | AC: 3846
TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions | AC: 3199
StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring | AC: 3204
PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection | AC: 3211
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding | AC: 3226
Learning Probabilistic Embeddings for Unsupervised Action Segmentation | AC: 3242
Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting | AC: 3256
ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space | AC: 3335
Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline | AC: 3348
From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution | AC: 3355
Off the Planckian Locus: Using 2D Chromaticity to Improve In-Camera Color | AC: 3428
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse | AC: 3477
Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding | AC: 3562
Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models | AC: 3608
When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators | AC: 3640
UniStitch: Unifying Semantic and Geometric Features for Image Stitching | AC: 3646
Heat Kernel Textures -- the Geodesic Gaussians That Do Not Splat | AC: 3652
How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning | AC: 3659
Axolotl3D: a Unified Framework for Faithful 3D Shape Completion | AC: 3723
SuperFlex: Deformable Superquadrics for Point Cloud Decomposition | AC: 3728
EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis | AC: 3736
Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations | AC: 3774
DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning | AC: 3797
Towards Spatial Supersensing in the Wild | AC: 3819
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models | AC: 3841
Video-Holmes: Can MLLM Think like Holmes for Complex Video Reasoning? | AC: 4209
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning | AC: 4392
RoMa v2: Harder Better Faster Denser Feature Matching | AC: 3967
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention | AC: 4126
P3-SAM: Native 3D Part Segmentation | AC: 4483
Distribution Matching Distillation Meets Reinforcement Learning | AC: 4350
TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning | AC: 4263
End-to-End Training for Autoregressive Video Diffusion via Self-Resampling | AC: 4177
Towards Scalable Pre-training of Visual Tokenizers for Generation | AC: 3997
RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models | AC: 4033
MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis | AC: 4315
Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain | AC: 4213
UniREditBench: A Unified Reasoning-based Image Editing Benchmark | AC: 4175
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision | AC: 3981
GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning | AC: 3970
MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots | AC: 3969
Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection | AC: 3942
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards | AC: 3927
LoMa: Local Feature Matching Revisited | AC: 4073
Pathwise Test-Time Correction for Autoregressive Long Video Generation | AC: 4396
RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion | AC: 4062
OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models | AC: 4317
SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder | AC: 3936
DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models | AC: 4441
Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos | AC: 3899
SD3.5-Flash: Distribution-Guided Distillation of Generative Flows | AC: 4024
TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning | AC: 4003
Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing | AC: 4254
DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents | AC: 4393
InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem | AC: 4456
PPTArena: A Benchmark for PowerPoint Editing | AC: 4154
Taming Camera-Controlled Video Generation with Verifiable Geometry Reward | AC: 3872
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels | AC: 4002
UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving | AC: 4301
VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM | AC: 3982
Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning | AC: 3990
Fast Sam 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery | AC: 4084
FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation | AC: 3869
One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control | AC: 4290
History-Aware Transformation of ReID Features for Multiple Object Tracking | AC: 4421
MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation | AC: 4334
MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training | AC: 3966
RubricRL: Simple Generalizable Rewards for Text-to-Image Generation | AC: 4070
SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows | AC: 4109
SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning | AC: 4466
TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding | AC: 4107
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing | AC: 4337
CFM: Language-aligned Concept Foundation Model for Vision | AC: 4197
EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing | AC: 4044
FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI | AC: 3953
FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography | AC: 3960
Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond | AC: 4047
IC-World: In-Context Generation for Shared World Modeling | AC: 4031
Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding | AC: 4438
Personalized Reward Modeling for Text-to-Image Generation | AC: 4339
Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks | AC: 4165
PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design | AC: 4148
Quick ViTs: Speeding up Vision Transformers through Equivariance | AC: 4032
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion | AC: 4457
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing | AC: 4308
EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation | AC: 4128
Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses | AC: 4264
In-Context Sync-LoRA for Portrait Video Editing | AC: 4473
IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation | AC: 3976
LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations? | AC: 4064
Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos | AC: 3891
Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors | AC: 4094
Tuning-free Visual Effect Transfer across Videos | AC: 4356
CameraAnything: Refilming Videos with Arbitrary Camera Control | AC: 3926
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation | AC: 4161
CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving | AC: 4408
DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding | AC: 4030
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection | AC: 3881
Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision | AC: 4303
E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework | AC: 4467
ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation | AC: 4211
FingerCap: Fine-grained Finger-level Hand Motion Captioning | AC: 3868
FitControler: Toward Fit-Aware Virtual Try-On | AC: 4018
Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation | AC: 3965
Glance: Accelerating Diffusion Models with 1 Sample | AC: 3879
Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces | AC: 4229
HippoCamp: Benchmarking Contextual Agents on Personal Computers | AC: 4004
Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments | AC: 4367
Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars | AC: 4099
Masked BRep Autoencoder via Hierarchical Graph Transformer | AC: 4133
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation | AC: 4251
OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better | AC: 3920
Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings | AC: 4454
RadarGen: Automotive Radar Point Cloud Generation from Cameras | AC: 4188
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding | AC: 4235
Silhouette-based Gait Foundation Model | AC: 3871
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On | AC: 3935
UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment | AC: 4316
When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition | AC: 4218
Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision | AC: 4119
City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion | AC: 4098
CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification | AC: 4076
CountEx: Fine-Grained Counting via Exemplars and Exclusion | AC: 3925
Decoupling Complexity from Scale in Latent Diffusion Model | AC: 4100
DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution | AC: 4406
DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces | AC: 3931
Driving like yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving | AC: 4140
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning | AC: 3910
Efficient Camera Pose Augmentation for View Generalization in Robotic Policy Learning | AC: 4217
EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents | AC: 4476
Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data | AC: 4471
Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models | AC: 4046
GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos | AC: 3890
GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision | AC: 3860
HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting | AC: 3877
HIVE: Understanding Post Hallucination Reasoning in Vision Language Models | AC: 4116
IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusion | AC: 3989
Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation | AC: 4487
Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation | AC: 4255
Layer-Aware Video Composition via Split-then-Merge | AC: 4053
Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval | AC: 4294
MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction | AC: 4429
MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images | AC: 4042
Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing | AC: 4121
Multi-View Foundation Models | AC: 3913
Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew | AC: 4065
OmniColor: A Unified Framework for Multi-modal Lineart Colorization | AC: 4348
OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents | AC: 4395
PanoSAM2: Lightweight Distortion- and Memory-aware Adaptions of SAM2 for 360 Video Object Segmentation | AC: 4198
Quantile‑Adaptive Temperature Scaling for Confidence Calibration | AC: 4026
RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs | AC: 4156
Recurrent Cross-View Object Geo-Localization | AC: 3957
Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation | AC: 4179
Safe Responses Matter: Output-Aware Safety Guardrail Mitigate Over-Refusal in MLLMs | AC: 4143
Seeing Fast and Slow: Learning the Flow of Time in Videos | AC: 4379
SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning | AC: 3988
SLER-IR: Spherical Layer-wise Expert Routing for All-in-One Image Restoration | AC: 4286
Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models | AC: 4424
SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models | AC: 4353
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence | AC: 4043
Stokes-Informed Diffusion for Robust Linear Polarization Estimation | AC: 4397
SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation | AC: 4300
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs | AC: 4204
Teaching an Agent to Sketch One Part at a Time | AC: 4305
TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches | AC: 4442
Training-Free Task Classification for Multi-Task Model Merging | AC: 4341
Video Generative Models as Geometry Learner | AC: 4384
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking | AC: 4145
WebEyeTrack: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization | AC: 4136
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE | AC: 5603
Visual Spatial Tuning | AC: 4687
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning? | AC: 5613
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models | AC: 4862
RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks | AC: 5252
MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning | AC: 4806
Reinforcing Video Reasoning with Focused Thinking | AC: 4876
EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation | AC: 5886
Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback | AC: 4907
Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment | AC: 5640
RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control | AC: 5820
Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild | AC: 5777
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations | AC: 5828
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning | AC: 5864
FindingDory: A Benchmark to Evaluate Memory in Embodied Agents | AC: 4986
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders | AC: 4516
OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents | AC: 4838
Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching | AC: 4993
Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning | AC: 5359
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference | AC: 5763
How to Teach Large Multimodal Models New Skills | AC: 4547
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention | AC: 4570
Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability | AC: 4821
OmniForcing: Unleashing Real-time Joint Audio-Visual Generation | AC: 5147
UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters | AC: 5352
MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing | AC: 5628
AnyView: Synthesizing Any Novel View in Dynamic Scenes | AC: 4566
WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation | AC: 4650
Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight | AC: 4793
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech | AC: 4836
Thinking in Streaming Video | AC: 4857
Grounding World Simulation Models in a Real-World Metropolis | AC: 4936
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing | AC: 5075
PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding | AC: 5160
EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use | AC: 5586
Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers | AC: 5980
Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation | AC: 4601
Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention | AC: 4766
FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models | AC: 4782
Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models | AC: 4982
Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration | AC: 5241
Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning | AC: 5951
Video Generation Models are General-Purpose Vision Learners | AC: 5984
Target-aware Image Editing via Cycle-consistent Constraints | AC: 4615
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance | AC: 4640
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources | AC: 4791
Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis | AC: 4833
LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation | AC: 5009
RAE-NWM: Navigation World Model in Dense Visual Representation Space | AC: 5038
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens | AC: 5256
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching | AC: 5433
Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow | AC: 5342
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding | AC: 5780
SLAM-Former: Putting SLAM into One Transformer | AC: 5556
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding | AC: 5552
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models | AC: 5042
GenRecal: Generation after Recalibration from Large to Small Vision-Language Models | AC: 4989
LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control | AC: 5570
Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention | AC: 4497
One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies | AC: 5978
Personalize Your Large Vision-language Models With In-context Prompt Tuning | AC: 5580
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations | AC: 4539
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training | AC: 5426
SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training | AC: 4992
SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization | AC: 4495
ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance | AC: 4815
Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models | AC: 5621
WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models | AC: 4908
Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D | AC: 4536
Continuous Adversarial Flow Models | AC: 4980
DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising | AC: 4994
ELT: Elastic Looped Transformers for Visual Generation | AC: 5671
Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection | AC: 4914
From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation | AC: 4492
MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning | AC: 4691
On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models | AC: 4861
RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation | AC: 4850
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video | AC: 4952
Rethinking Reward Signals in Video GRPO: When Scores Become Targets | AC: 5060
The Telephone Game: Evaluating Semantic Drift in Unified Models | AC: 5689
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning | AC: 5006
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning | AC: 4827
CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management | AC: 5915
Early Estimation of Language to Latent Alignment in Diffusion Models | AC: 5787
EgoCogNav: Cognition-aware Human Egocentric Navigation | AC: 5014
EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation | AC: 5713
Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models | AC: 5335
GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models | AC: 4694
HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task | AC: 5762
HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks | AC: 4630
MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training | AC: 4577
MOOZY: A Patient-First Foundation Model for Computational Pathology | AC: 4955
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video | AC: 5312
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion | AC: 4605
Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective | AC: 4563
Representation Alignment for Just Image Transformers is not Easier than You Think | AC: 4716
Small Vision-Language Models are Smart Compressors for Long Video Understanding | AC: 5596
SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation | AC: 5604
StrucTab: A Structured Optimization Framework for Table Parsing | AC: 4626
TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings | AC: 5034
λSplit: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy | AC: 4844