Eccv 2026 Hitmem

Summary

A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attention Paper: ... Paper: RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Models. Diffusion to Obfuscation: Time-Adaptive Synthesized Generation Against Gradient Leakage Attacks in Federated Learning. OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning. Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors. DART: Deformable Adaptive Reasoning with Temporal Queries for Online Skeleton-Based Action Recognition. TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models. CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization. Video for paper: VLA Knows Its Limits. Project link: hatchetproject.github.io/autohorizon/ Our work, “Scaling Multi-Reference Image Generation with Dynamic Reward Optimization,” has been accepted to