OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 11 days ago • 225
Recovering Reliable Supervision via Critique-Guided On-Policy Distillation Paper • 2610.20572 • Published 10 days ago • 46
Less from More: Reinforcing Sparse Video Reasoning from Dense References Paper • 2610.10893 • Published 17 days ago • 13
JevGPT: Thinking Fast and Slow in Autonomous Research Paper • 2610.18272 • Published 11 days ago • 41
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published 11 days ago • 341
LeWAM: End-to-End World and Action Modeling with JEPAs Paper • 2610.12818 • Published 16 days ago • 33
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 24 days ago • 150
VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction Paper • 2610.06293 • Published 19 days ago • 146
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment Paper • 2609.38972 • Published 24 days ago • 30
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting Paper • 2609.29792 • Published 30 days ago • 29
Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers Paper • 2608.26762 • Published 28 days ago • 24
PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs Paper • 2609.34715 • Published 26 days ago • 65
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 25 days ago • 208