AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models Paper • 2607.02269 • Published 3 days ago • 7
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250
Reflective Prompt Tuning through Language Model Function-Calling Paper • 2605.21781 • Published May 20 • 9
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 238
Ethical Hyper-Velocity (EHV): A Provably Deterministic Governance-Aware JIT Compiler Architecture for Agentic Systems Paper • 2605.17909 • Published May 18 • 4
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation Paper • 2605.11739 • Published May 13 • 60