Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression Paper • 2608.04569 • Published 9 days ago • 12
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone Paper • 2607.25895 • Published 17 days ago • 156
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 23 days ago • 311
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model Paper • 2607.17977 • Published 25 days ago • 198
Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms Paper • 2607.07769 • Published Jul 8 • 10
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras Paper • 2607.12993 • Published about 1 month ago • 131
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published about 1 month ago • 232
RedVox: Safety and Fairness Gaps in Speech Models Across Languages Paper • 2606.26968 • Published Jun 25 • 16
OpenRath: Session-Centered Runtime State for Agent Systems Paper • 2606.19409 • Published Jun 17 • 78
FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining Paper • 2606.20506 • Published Jun 18 • 28
RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes Paper • 2606.00828 • Published May 30 • 11