Demystifying Agent Skills: Why They Work-Until They Don't Paper • 2608.14036 • Published 22 days ago • 169
WorldClaw: Agentic 3D Open-World Generation at Scale Paper • 2608.05248 • Published about 1 month ago • 84
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey Paper • 2607.21655 • Published Jul 22 • 193
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing Paper • 2607.18934 • Published Jul 21 • 6
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill Paper • 2607.12625 • Published Jul 15 • 81
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 313
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model Paper • 2607.17977 • Published Jul 20 • 198
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published Jul 19 • 167
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras Paper • 2607.12993 • Published Jul 14 • 131
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published Jul 14 • 235
ACID: Action Consistency via Inverse Dynamics for Planning with World Models Paper • 2607.02403 • Published Jul 2 • 24
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 178
OpenSTBench: Beyond Semantic Evaluation for Speech Translation Paper • 2605.30792 • Published May 29 • 4
Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs Paper • 2605.24681 • Published May 23 • 5