SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? Paper • 2605.30329 • Published 7 days ago • 7
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents Paper • 2605.25971 • Published 10 days ago • 16
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published 16 days ago • 185
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 22 days ago • 270
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 28 days ago • 233
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents Paper • 2605.05185 • Published 29 days ago • 101
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation Paper • 2604.24764 • Published Apr 27 • 118