Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning Paper • 2606.24428 • Published 3 days ago • 48
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published 9 days ago • 135
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 13 days ago • 72
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper • 2606.08063 • Published 20 days ago • 79
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 16 days ago • 118
Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path Paper • 2606.07271 • Published 21 days ago • 2
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 18 days ago • 102
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published 22 days ago • 67
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain Paper • 2605.23895 • Published May 22 • 52
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published about 1 month ago • 431