📂 Others

🎞️ ECCV2026 · 57 paper notes

📌 Same area in other venues: 📷 CVPR2026 (105) · 🔬 ICLR2026 (115) · 💬 ACL2026 (3) · 🧪 ICML2026 (70) · 🤖 AAAI2026 (117) · 🧠 NeurIPS2025 (121)

🔥 Top topics: Adversarial Robustness ×6 · Diffusion Models ×3 · Few-/Zero-Shot Learning ×2 · Face & Gaze ×2

Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation

Addressing the long-standing issue where optical tactile sensors struggle to distinguish fine-grained contact states, this paper reveals that the dot product of "transient motion" and "cumulative motion" can explicitly differentiate states such as "making contact / stable contact / releasing contact." Based on this, a Tactile Motion Correlation (TMC) representation is proposed. Using a Mixture-of-Transformers, TMC is integrated as an independent modality alongside vision, raw touch, and proprioception, achieving higher success rates across four real-world contact-rich manipulation tasks.

Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints

Articulat3D proposes a two-stage optimization framework to reconstruct interactive digital twins of articulated objects from casual monocular videos. The first stage performs structured, part-level motion decomposition on 3D point trajectories using low-dimensional motion bases. The second stage constrains the motion to satisfy physical rigid-body rules using explicit kinematic primitives (axes, pivots, and frame-wise scalars of revolute/prismatic joints). It achieves state-of-the-art (SOTA) accuracy on both synthetic and real-world data without requiring static pre-scans.

Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras

This paper proposes the first event camera wide-baseline feature matching model that achieves zero-shot generalization across datasets. It learns highly efficient multi-temporal-scale event features using a separable spatial-temporal attention backbone (TAg) and sparse-aware token adaptive pruning (SETS). Trained on a large-scale synthetic (E-MegaDepth) and real-world (ECM) wide-baseline dataset, it outperforms the previous state-of-the-art by 37.7% on multiple benchmarks.

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

Proposes FeDLaS (Feature-modulated Bidirectional Label Smoothing), which utilizes the L1 norm of hidden layer features as a confidence proxy to bypass the validation limits of softmax saturation. Combined with bidirectional calibration gating, it dynamically determines the overconfidence/underconfidence state of each sample in real-time, adaptively modulating the label smoothing strength per sample to significantly reduce ECE and AECE while maintaining Top-1 accuracy.

Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification

This paper reinterprets entropy-based test-time adaptation (TTA) as a posterior inference problem under underspecification — many low-entropy solutions exist with drastically different decision boundaries — and instead of committing to a single point estimate it maintains K adaptation particles that only update normalization layers, explores different low-entropy basins, applies diversification at the output, parameter, optimizer, and input levels to prevent collapse, and aggregates the multi-hypothesis predictions at inference; it consistently beats Tent / SAR / DeYO on ImageNet-C under batch size one, label shifts, and mixed shifts, and works as a plug-and-play wrapper for existing TTA methods.

Quantile‑Adaptive Temperature Scaling for Confidence Calibration

QaTS chooses a sample's temperature from its confidence quantile in the calibration set, fitting only two positive parameters to improve calibration while preserving class predictions; on CIFAR-100 with RN-50, for example, ECE falls from 5.32 with standard TS to 2.56.

Color Pass-Through via Camera-Display Coupling

Addressing noticeable chromaticity and lightness gaps when capturing real-world scenes on smartphone cameras and viewing them on screens, this paper proposes an end-to-end Color Pass-Through framework that couples camera and display as a unified system, utilizing a lightweight neural projector and rank-1 camera-null space color correction with a single-step observer calibration to faithfully reproduce perceived scene colors.

Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification

To tackle the failure of conventional active learning caused by severe inter-class visual overlap in fine-grained image classification, DECERN decouples structural stability and category directionality via local feature fusion, coupled with uncertainty-weighted clustering and calibration diversity to achieve state-of-the-art sample selection under tight annotation budgets.

CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

CubicSplat resolves the gradient seesaw between forward geometric exactness and backward gradient conditioning in differentiable vector graphics through error-bounded forward relaxation, replacing Bézier closest-point root solvers with an \(\mathcal{O}(S^{-2})\) polyline surrogate to enable closed-form distance evaluation, achieving up to 4× faster training and over 2 dB PSNR gains on closed-fill benchmarks.

Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s)

Rather than treating rolling-shutter distortions as artifacts to be eliminated, this paper introduces a correspondence-free back-projection framework that decouples translation from rotation, enabling high-precision estimation of 3D velocity and spin for high-speed spherical objects from a single rolling-shutter image.

From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift

Addressing the failure of classical PU learning under severe distribution overlap caused by covariate shift, S-PUNA introduces a geometry-aware framework that expands positive and negative pseudo-labels symmetrically on ViT feature manifolds, guided by a spectral entropy stopping criterion to prevent drift and rival fully supervised methods.

Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

This paper proposes Geometric Gradient Rectification (GGR), a plug-and-play gradient-space rectification framework. Using the supervised gradient as an anchor, GGR projects conflicting unsupervised auxiliary gradients onto a safe half-space. This ensures that auxiliary updates remain first-order non-adversarial compared to the supervised direction on selected parameter blocks, simultaneously enhancing closed-set generalization and open-set robustness without relying on accurate OOD detection.

Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges

To tackle pseudo-label drift and confirmation bias in realistic long-tailed semi-supervised learning, this paper proposes Gaussian Bridge Consistency (GBC) to establish class-conditional latent interpolation paths between unlabeled samples and reliable anchors, coupled with confidence-guided BridgeMix for superior tail-class generalization.

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

This paper proposes the Geometry-Anchored Transport Framework, which shifts feature transport from a decoupled post-processing paradigm to training-time geometric constraints. By using analytical geometric anchors (closed-form solutions of the Sylvester equation) to suppress macro-anisotropic drift, and combining with topology-aware evolution to constrain local manifold degradation, it stably transports old-class Gaussian statistics under exemplar-free constraints to achieve reliable Mahalanobis evaluation.

Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization

IS-SNN stabilizes the firing rate of deep spiking neural networks without any activation normalization layers (Batch Normalization) through topology-aware weight standardization and modified residual connections. After training, the standardization operations are folded into static weights, achieving zero normalization overhead during inference. It achieves 68.05% accuracy on ImageNet while reducing FPGA LUT resource consumption by 96.4%.

Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification

Addressing the vulnerability of isolated building damage classifiers to appearance domain shifts and the propensity of naive graph attention to oversmooth damage boundaries, this paper proposes a graph attention framework incorporating a disaster-type-conditioned multi-scale spatial kernel prior and a residual Moran's I de-correlation regularizer, preserving local evidence while adaptively aggregating neighbourhood context across diverse disaster types.

Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension

Addressing the representation mismatch where weakly supervised referring expression comprehension (WREC) flattens relational context into unary anchors, SVCR explicitly constructs a structured visual representation space with decoupled unary object representations and pairwise relational representations, achieving state-of-the-art grounding accuracy via multi-granular compositional alignment without bounding-box annotations.

Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition

This paper reveals that city-scale visual place recognition datasets suffer from a severe long-tail geographic distribution problem (with a head-to-tail category sample ratio up to 300:1). It proposes the DAPR framework, which uses a Low-visit Bias (LB) loss for inverse frequency weighting and classifier bias calibration during the training phase, and employs Characteristic Function Distance (CFD) in the frequency domain for distribution-aware re-ranking during inference. DAPR outperforms the previous state-of-the-art hybrid pipeline by 18.3% R@1 on the SF-XL benchmark.

LumiTokens: 3D Relighting via Token-Space Lighting Transformation

LumiTokens reformulates 3D relighting as a direct closed transformation within an unstructured latent token space, utilizing self-attention between scene tokens and Plücker light-ray tokens to achieve view-consistent relit novel view synthesis and seamless progressive multi-light composition without explicit 3D geometry or rendering equations.

MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer

To tackle cross-region makeup spillover, concept confusion between source identity and reference makeup, and scarce paired supervision, MagicMakeup introduces a Diffusion Transformer framework with Token-Aligned Region Gating and Cross-Modal Perception Guidance alongside a 1024×1024 regional makeup-removal data construction pipeline for high-fidelity facial makeup transfer.

MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts

Addressing the severe negative transfer and deployment bottlenecks of conventional per-action assessment pipelines, MoAKE introduces the first unified all-in-one action quality assessment framework that couples segment-aware prototype aggregation, adaptive multi-granularity relationship modeling, and label-free soft routing to achieve positive cross-action transfer, outperforming existing methods on both unified benchmarks and zero/few-shot generalization.

Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness

Presents MIEdit, a training-free diffusion SDE inversion framework combining high-order multi-history-step predictor-corrector sampling, power-interpolated inference noise scheduling, and inversion-time automatic semantic angle masking (IASM) to achieve superior editing plasticity and background preservation under minimal function evaluations.

NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics

This paper proposes NURBS Splatting, which adaptively samples NURBS curves along the arc length as isotropic Gaussian kernels and differentiably renders them using a tile-based Gaussian splatting rasterizer. This integrates rational weights and non-uniform knot vectors into 2D image-space end-to-end optimization for the first time, significantly outperforming existing polynomial primitive-based methods in tasks such as calligraphy reconstruction, layered image vectorization, and single-stroke image abstraction.

Parallax Portrait Matting

Addressing the severely ill-posed nature of portrait matting under complex background textures, this work introduces a practical two-frame approach using burst-induced parallax, employing an asymmetric architecture that directly fuses reliable background alignment while compensating for noisy foreground alignment via cross-attention.

PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos

Addressing ambiguous region matching under view/pose variations and fragmented regions in animation paint-bucket colourisation, PeCA introduces a training-free, plug-and-play test-time inference framework combining target-conditioned active reference expansion, Top-k soft voting probability aggregation, and cycle-consistent temporal fusion to consistently boost colourisation accuracy across both task-trained and frozen foundation models.

Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision

Pointer-CAD v2 proposes the Plan-Then-Construct framework, which decouples CAD generation into two stages: "first plan dimension parameters, then construct geometry by retrieving parameters via pointers." This completely eliminates the precision loss caused by numerical parameter quantization in traditional command sequence methods, significantly outperforming all baselines across vertex, edge, and face-level geometric precision metrics.

PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications

PolarAPP is the first framework to jointly optimize polarization demosaicking and downstream polarimetric applications (such as surface normal estimation and de-reflection), breaking the traditional bottlenecks of low-quality regrouped datasets and task-agnostic demosaicking through bi-level meta-learned feature alignment and equivalent imaging transformation priors.

QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning

QASA introduces an unsupervised slot-quality metric based on competitive attention purity alongside gated decoders, decoupling slot selection from reconstruction to achieve dynamic object discovery that surpasses fixed-\(K\) baselines without tuning slot counts.

RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement

Addressing the vulnerability of video-based remote physiological measurement under challenging lighting, skin tone, and motion, as well as the high deployment overhead of radar hardware at inference, RPM-Distill leverages synchronized radio-frequency radar as privileged training information, decouples spectral physiological constraints (fundamental peak, background noise, and morphology sharpness), and employs a bilevel meta-learned spectral policy network to adaptively gate and reweight distillation, achieving robust video-only physiological measurement.

SOMA: From Surface Observations to Muscle Anatomy

Addressing the fundamental limitation that conventional digital human models are restricted to the outer skin surface while finite element simulations are computationally prohibitive, SOMA presents the first data-driven framework to infer dynamic internal muscle deformations directly from multi-view RGB visual observations; using the newly captured SKIM dataset with a custom ArUco marker suit, decoupled non-linear blendshapes, and multi-physical geometric priors, it enables real-time, penetration-free, anatomically grounded musculoskeletal animation driven solely by skeletal pose.

Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations

Starting from the steady-state response of a forced damped harmonic oscillator, this paper derives a physically driven activation function, FDHO, which couples the activation amplitude and frequency through a second-order transfer function. This coupling produces an implicit spectral gating mechanism: the self-interaction term of the damping factor gradient constantly closes the spectral gate, whereas the signal term opens the gate only when the target displays coherent frequency components. This enables automatic distinction between signal and noise without any explicit regularization or task-specific hyperparameter tuning, achieving state-of-the-art (SOTA) or competitive performance across tasks like signal fitting, denoising, CT reconstruction, and super-resolution.

Under One Sun: Multi-Object Generative Perception of Materials and Illumination

MultiGP addresses the ill-posed radiometric disentanglement problem in single-image inverse rendering by leveraging the physical consensus of multiple objects sharing the same scene illumination, using a cascaded diffusion architecture with Coordinated Scheduling and Axial Attention to jointly sample diffuse textures, uniform reflectances, and high-frequency illumination.

Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization

This work proposes Vector Scaffolding, a hierarchical optimization framework that addresses the area-boundary gradient imbalance via Interior Gradient Aggregation, densifies curves from coarse to fine according to natural image power laws using Progressive Stratification, and applies a 50x learning rate scaling via Rapid Inflation Scheduling to achieve 2.5x speedup and a ~1.4dB PSNR improvement, reframing differentiable vectorization from "flat pixel matching" to "structured topological construction."

VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion

Addressing the ill-posed inverse problem of foreground shadow generation in image composition, VSDiffusion introduces a two-stage visibility-constrained diffusion framework that combines residual control prior injection, shadow-gated cross-attention, and spatially soft prior-weighted loss to achieve geometrically consistent, sharp shadows with high computational efficiency.

Compact and Structurally Transparent Cervical Cytology with Geometry-Driven Features and Closed-Form Attention

The paper models the clinical cervical cytology screening workflow into an intrinsically transparent network architecture, deriving closed-form spatial attention via free-energy minimization over four diagnostic potential maps and extracting auditable representations through a geometry-driven analytic backbone, achieving SOTA accuracy on DSCC, SIPaKMeD, and Herlev with only 2.2M parameters.

DeCo: Zero-Shot Anomaly Generation through Decoupling and Recoupling

Addressing the scarcity of real industrial defects and the issues of inaccurate anomaly acquisition and uncontrolled fusion in prior work, DeCo decouples pure anomaly structure from source products via DR-Flow and PI-Flow, binding it to an abnormal token, and explicitly recouples it with target product textures via hybrid LoRA injection and Product Compatibility Correction (PCC), significantly advancing downstream detection SOTA on MVTec AD and VisA.

Deep Noise Label Learning via Effective Rank Reduction

Addressing the failure of existing transition-matrix methods that overlook semantic class clustering and assume an unconstrained full rank, this paper introduces the Low-Effective-Rank Noisy-Label Learning (LENL) framework, which enforces nuclear-norm regularization on the noise transition matrix and develops a decomposition-free Newton–Schulz optimizer to eliminate SVD gradient instability while providing provable generalization guarantees.

Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework

Addressing the vulnerability of conventional video fusion pipelines where modality-specific degradations impair temporal motion estimation, DRT-VF advocates a "fusion-first" paradigm using a one-step rectified-flow diffusion framework paired with hierarchical temporal modeling, achieving high-fidelity and flicker-free video fusion.

Disentangling Rotation and Translation from SE(3)-Equivariant Features for Shape Assembly

To resolve the performance degradation and poor generalization caused by entangled rotation and translation in 3D shape assembly, this paper proposes the SOT encoder, which decouples rigid motions into an SO(3)-equivariant rotation feature via null-space projection and a T(3)-equivariant translation feature via translation loss and direct algebraic subtraction.

EVEE: Event-Based Online Adaptation for Matching on Unknown Targets

Addressing the severe degradation of offline-trained matchers on previously unseen targets and their frozen inference weights, EVEE turns short-window event activity into label-free online proxy supervision, pairing a multi-threaded Training Warehouse (TraW), a decayed Event Voting Bank (EVB), and a negative-only ReWeight gate to deliver 51.3 FPS unknown-target matching with a 1.9% pose ACC/AUC gain over state-of-the-art baselines.

Event-based Gaze Control Systems for Real-time Spin Estimation in Professional Ball Games

To overcome severe motion blur, narrow field of view, and translation-rotation conflation in high-speed sports, this paper presents an active gaze control system coupling an event camera, dual galvanometer mirrors, and an electrically tunable liquid telephoto lens, combined with spherical contrast maximization and an uncertainty-aware CNN to achieve 750 Hz throughput, 3 ms latency, and 1.2% magnitude / 1.5° axis error on unmodified spinning balls.

From Local to Global: A Progressive Reconstruction Network for Diffractive Snapshot Spectral Imaging

Addressing the severe spatial non-uniformity of diffractive snapshot spectral imaging (DSSI) where coded signals concentrate in texture-rich regions, LGSRNet introduces a progressive two-stage network that extracts local cues via convolutional blocks and propagates them globally, delivering state-of-the-art spectral fidelity while cutting FLOPs and latency.

FUSE: Filter-Free Unified Spatiotemporal Estimation of SpO2 via Wave-Transport Modeling

Addressing the vulnerability of conventional contactless SpO2 methods that rely on static frequency-domain filtering, FUSE introduces a filter-free wave-transport dynamical system that constrains pulsatile AC components via harmonic ODEs, regularizes spatial blood flow via advection PDEs, and achieves state-of-the-art accuracy across variable frame rates through continuous-time neural modeling.

General Self-Calibration with Varying Intrinsics

This paper introduces a unified algebraic framework for multiview camera self-calibration with varying intrinsics by pushing structured parameter-space priors forward into dual image of the absolute conic (DIAC) space and sampling locally independent square subsystems via Jacobian rank analysis to reliably solve overdetermined Kruppa systems.

HERO: Heterogeneous Evidential Robust Object-Level Collaborative Perception

Addressing the heavy communication overhead of feature-level fusion and the vulnerability of standard late fusion under pose bias and communication latency in heterogeneous multi-agent systems, HERO introduces an evidential proposal protocol that decouples fusion into Beta-sum semantic evidence accumulation and max-evidence geometry selection, matching feature-level accuracy with only ~2 KB/frame bandwidth while demonstrating superior robustness under perturbations.

High-Throughput Event-Based Feature Detection and Tracking on an Embedded CPU

Addressing the severe tension between the massive event rates of neuromorphic cameras and the tight compute limits of edge devices, SPEEDTrack presents a learning-free, GPU-free pipeline that leverages motion-defined concurrent slices and task-graph scheduling to surpass benchmark event throughput on an embedded CPU.

LIIFusion: Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation

LIIFusion decouples generative multi-exposure fusion into a low-resolution global diffusion stage with adaptive exposure correction and a high-resolution continuous implicit neural refinement stage, eliminating costly patch-wise sampling to achieve a 3.5× speed-up while improving structural fidelity and perceptual quality.

Local Spacing-Aware Hungarian Matching for Stable Point-Supervised Crowd Counting

Addressing severe assignment ambiguity and cross-epoch training oscillation caused by globally uniform geometric matching costs in dense point-supervised crowd counting, this paper proposes SAH-matcher, which dynamically rescales target geometric matching costs via a k-NN local spacing prior, combined with CAS, HR, and IR process-level diagnostic metrics to substantially boost counting and localization accuracy with zero inference overhead.

LoRC: Detecting AI-Generated Images via Low-Rank Collapse in the Semantic-Residual Space

Addressing the failure of semantic forensics caused by modern generators over-aligning with macroscopic semantics, this paper identifies an architecture-agnostic low-rank collapse signature in the orthogonal semantic-residual subspace induced by terminal decoding bottlenecks, proposing the LoRC framework with orthogonal decomposition, low-rank attention, and subspace separation to achieve 97.0% zero-shot accuracy across 39 unseen generators.

Making Partial-Label Datasets Easier: A Simple Yet Highly Effective Data Augmentation for Deep Partial-Label Learning

Addressing the core difficulty in partial-label learning where feature and candidate-label manifolds are tightly coupled in local neighborhoods, this paper introduces the Local Ambiguity Degree (LAD) metric to quantify disambiguation hardness and develops UMiP, a lightweight plug-and-play augmentation framework using dominant mixing and candidate-constrained renormalization that provably reduces dataset ambiguity and introduces implicit regularizations to boost deep PLL models.

Maximum Spanning Tree Guided Confidence and Sparse Graph for Robust Noisy Label Learning

Addressing the issues of overly dense connectivity amplifying noise and boundary hard samples propagating errors in conventional graph-based learning with noisy labels, this paper proposes the Maximum Spanning Tree Guided Confidence and Sparse Graph Network (MST-GCSN), which leverages an MST topological skeleton, confidence-gated propagation, and progressive multi-scale label prediction to achieve robust label refinement under severe label noise.

Mitigating Radar-Inertial Calibration Ambiguities via SO(3) Manifold Steering

RadarCalib introduces a targetless, plug-and-play Radar-inertial spatiotemporal calibration framework that circumvents point-matching ambiguities by extracting rotation-induced azimuthal drift in the spectral domain via temporal synthetic aperture (TSA), enforcing cycle-invariant manifold regularization alongside Doppler velocity and pose consistency on SE(3) to achieve sub-degree rotational and centimeter-level translation accuracy.

Physics-Guided Deep Learning for Linear Mueller Matrix Acquisition

Addressing the low efficiency of traditional Mueller matrix polarimetry that requires multiple incident polarization switches, this paper proposes a physics-guided two-stage framework that estimates pBRDF parameters from single-shot four-channel polarization images to construct an analytical initialization and refines it via residual learning into an accurate, physically plausible \(3 \times 3\) linear Mueller matrix.

Taming Dynamic Clutter: Variance-Driven Adaptive Gain Control for Bio-inspired Small Target Detection

Addressing the catastrophic "false alarm collapse" in bio-inspired Small Target Motion Detection (STMD) caused by non-stationary dynamic clutter, this paper proposes a plug-and-play architecture integrating LPTC population-coding macro-motion decoupling with micro-scale variance-driven Adaptive Gain Control (AGC), achieving near-total false alarm eradication and state-of-the-art precision.

Towards Reliable Multi-Label Classification via Conditional Dependency Modeling

Addressing the structural bias and probability miscalibration caused by the prevailing conditional independence assumption in multi-label classification, this work theoretically proves that this bias is proportional to pairwise label covariance, and proposes Pairwise Correlation Difference (PCD) alongside BCE as Correlated Multi-Label Loss (CMLL) to achieve well-calibrated predictions without sacrificing classification accuracy.

Training-free Controllable Motion Generation under Heterogeneous Constraints

This paper introduces Motion-Inference-as-Control (MIC), a training-free controllable motion generation framework that casts the diffusion sampling process as a stochastic optimal control problem, unifying non-differentiable criterion-based rules and differentiable objective-based constraints within a shared control interface while resolving multi-constraint conflicts via bilevel coordination.

Weight Feedback Computes the Exact Jacobian Transpose in Modern Deep Networks

Revealing that the exact Jacobian transpose factors into purely local quantities under frozen normalization statistics for modern deep layers, this paper introduces WF-Act-PC—an autograd-free predictive coding framework that exhibits positive depth scaling and matches or outperforms tuned backpropagation on deep convolutional networks.