Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos Paper • 2610.30866 • Published 26 days ago • 15
Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning Paper • 2611.03602 • Published 14 days ago • 26
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets Paper • 2609.37775 • Published Sep 29 • 16
Think Before You Score: Thinking Reward Model for Visual Generation Paper • 2609.37372 • Published Sep 29 • 58
RefCaptioner: Multi-Reference Image-Grounded Video Captioning Paper • 2607.28509 • Published Jul 30 • 29
Beacon: Knowing When and How to Perform Agentic Visual Reasoning Paper • 2607.28595 • Published Jul 30 • 53
KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation Paper • 2607.14202 • Published Jul 15 • 39
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation Paper • 2607.14189 • Published Jul 15 • 29
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV Paper • 2605.26244 • Published May 25 • 35
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling Paper • 2605.13062 • Published May 13 • 33
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization Paper • 2605.10780 • Published May 12 • 32
VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining Paper • 2603.15030 • Published Mar 16 • 21