The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 6 days ago • 391
Learning Where to Split: Dynamic Band Splitting for Audio Source Separation Paper • 2610.14993 • Published 22 days ago • 54
Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression Paper • 2610.09788 • Published 24 days ago • 24
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations Paper • 2610.00994 • Published about 1 month ago • 32
ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context Paper • 2609.36684 • Published Sep 29 • 20
EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset Paper • 2609.17189 • Published Sep 15 • 21
τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation Paper • 2608.16885 • Published Aug 17 • 17
TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement Paper • 2608.11951 • Published Aug 12 • 7
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 196
CAPEval: A Decoupled Caption Evaluation across Understanding and Generation Paper • 2608.02589 • Published Aug 3 • 25
Scaling Properties of Text Conditioning in Visual Generation Paper • 2607.29679 • Published Jul 31 • 41