Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published 3 days ago • 101
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 7 days ago • 62
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper • 2606.08063 • Published 14 days ago • 78
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning Paper • 2606.07190 • Published 15 days ago • 35
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 10 days ago • 113
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published 16 days ago • 52
OpenComputer: Verifiable Software Worlds for Computer-Use Agents Paper • 2605.19769 • Published May 19 • 84
CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models Paper • 2605.23699 • Published 29 days ago • 11