Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper • 2606.08063 • Published 9 days ago • 75
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 5 days ago • 110
Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path Paper • 2606.07271 • Published 10 days ago • 2
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 7 days ago • 98
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published 11 days ago • 52
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain Paper • 2605.23895 • Published 24 days ago • 52
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 19 days ago • 423