From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models Paper • 2607.06553 • Published 11 days ago • 20
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published 13 days ago • 78
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 22 days ago • 168
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History Paper • 2606.08671 • Published 27 days ago • 46
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors Paper • 2606.32029 • Published 20 days ago • 14
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 177
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems Paper • 2606.18837 • Published Jun 17 • 58
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published Jun 13 • 74
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published Jun 17 • 141
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Paper • 2606.12087 • Published Jun 10 • 79