📡 Signal & Communications

📷 CVPR2026 · 7 paper notes

📌 Same area in other venues: 🧠 NeurIPS2026 (1) · 🎞️ ECCV2026 (10) · 🔬 ICLR2026 (7) · 🧪 ICML2026 (2) · 🤖 AAAI2026 (3) · 🧠 NeurIPS2025 (5)

CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space

CLAY proposes a training-free method for conditional visual similarity calculation, which modulates similarity by constructing a text-conditioned subspace within the VLM embedding space. This approach adapts to different retrieval conditions without recomputing database features and supports multi-condition retrieval.

AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation

This paper proposes AcTTA, a test-time adaptation framework based on dynamic activation function modulation. By reparameterizing traditional fixed activation functions into a learnable form—incorporating activation center shifts and asymmetric gradient slopes—the model adaptively adjusts activation behavior during inference to handle distribution shifts. AcTTA consistently outperforms normalization-based TTA methods on CIFAR10-C, CIFAR100-C, and ImageNet-C.

GAI-GS: A Wireless Channel Prediction Framework Injecting Ray-Object Interaction into 3DGS via Geometric Algebra Attention

GAI-GS treats 3D Gaussian Splatting (3DGS) as a wireless radiation field. It utilizes a Geometric Algebra (GA)-based attention tokenizer to implicitly model physical ray-object interactions—such as reflection, diffraction, and transmission—within the scene. These interaction features are then injected as residuals into Gaussian attributes via a dual-branch scene mapping network, achieving SOTA performance in MAE and SSIM across several real-world indoor RSSI and spatial spectrum datasets.

Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis

GRaF transfers the NeRF concept to the RF domain. By introducing a theorem stating that "the spatial spectrum of a target transmitter can be approximated by interpolating the spectra of neighboring transmitters," it transforms the "per-scene retraining" NeRF into a generalizable latent RF radiance field. Leveraging a geometry-aware Transformer to encode neighbor spectra and complex-valued neural ray tracing to reconstruct the spatial spectrum, GRaF outperforms NeRF2 in both single-scene and unseen-scene settings.

Ghosts in the Point Clouds: De-glaring LiDAR in the Transient Domain

Addressing internal multipath glare in new-generation solid-state single-photon LiDAR—which creates "ghost" objects and obscures real ones—this paper models glare as a linear, scene-independent Glare Spread Function (GSF). The method processes low-level echoes per pixel before point cloud formation: it uses the method of moments to correct photon pileup distortion, predicts glare contributions with the GSF, and applies a binomial likelihood confidence measure to distinguish true signals from glare. It is training-free and deployable on unmodified commercial sensors.

Task-Driven Implicit Representations for Automated Design of LiDAR Systems

This work encodes LiDAR sensor configurations as points in a continuous 6D design space, uses normalizing flows to learn an implicit density of "which designs are most useful for a given 3D task", and then fits Gaussian mixture "sensors" to this density via EM. This enables the automated generation of LiDAR systems tailored to tasks such as face scanning, robotic arm tracking, or warehouse detection under arbitrary physical constraints, while reducing data bandwidth by up to approximately 90% (1/10).

X-band Radar Non-Line-of-Sight Imaging

This work replaces optical and millimeter-wave (mmWave) sensors with 10 GHz X-band radar for non-line-of-sight (NLOS) imaging. By leveraging longer wavelengths, it transforms "diffuse reflection" on rough walls into "specular reflection." A neural network utilizing "dense prediction + geometric-aware residual reconstruction" is employed to counter the low angular resolution inherent in long wavelengths, extending the effective "corner imaging" distance from a few meters (optical) to 40 m in real-world scenarios.