Conventional flow-based vision-language-action (VLA) models support expressive continuous action generation but rely on multi-step refinement to produce each action chunk, increasing latency in online robot control. To address this issue, we introduce DriftingVLA, a native one-step VLA that generates a complete action...
ReTouch is introduced, a vision-language-action model (VLA) that supports contact-rich dexterous manipulation through tactile predictions continually refined online using execution-time feedback, and keeps tactile predictions aligned with evolving physical interactions, enabling responsive action correction and improvi...
Shi-Qi Zhang, Xin Zhang, Yedong Shen et al.· 4 citations
Overall, Code2Skill transforms procedural knowledge embedded in repositories into grounded, verifiable, and transferable agent skills, providing initial evidence that the pipeline can expand with the growing volume of AI-generated software.
Yong-Qi Tong, Pan Wang, Hang Wang et al.· 1 citation
Next-turn user reactions provide actionable local credit for improving multi-turn user-interacting agents and improves the nine-domain $\tau$-family average across three independently trained runs.
Yi-Wen Zhao, Zhihao Wen, Yuchen Mao et al.· 1 citation
IMPACT is introduced, a scalable Interaction-aware Model training framework with Prior-guided Attention Calibration and Targeting, which consistently outperforms the corresponding MSE-trained baselines, improving interaction fidelity, physical plausibility, and visual quality.
Rong-Ze Tang, Jian-Jie Fang, Zhao-Lu Wang et al.· 1 citation
Causal Action Effect Reweighting (CAER), a general training paradigm that redistributes supervision toward the tokens whose predicted future is causally affected by the action, is introduced.
Jian-Jie Fang, Xvyuan Liu, Zi-You Wang et al.· 0 citations
WorldScape Policy 2.0 is introduced, a controllable WAM with reasoning-augmented long short-term memory and fine-grained instruction following and in-context adaptation that demonstrates superior capabilities in long-horizon autonomous planning, fine-grained instruction following and in-context adaptation.
Hai-Sheng Su, Zong-Dai Liu, Xin Jin et al.· arXiv.org· 2 citations
Safety Harness Evolution (SHE) is proposed, a framework that learns evolving safe boundaries from rollout trajectories and introduces an attribution-guided evolution loop that converts trajectory failures into structured diagnoses, learns artifact-specific boundary refinements, and selects evolved harnesses through saf...
Wanying Qu, Qing-Hua Mao, Yu Li et al.· 5 citations
DARC is proposed, a diagnosis-guided recovery harness that profiles task-family failure modes, prunes mismatched interventions from a shared recovery library, and freezes a verifier-selected success-cost policy for deployment, providing a practical route toward more reliable agents in domains where compiler-like feedba...
Pan Wang, Yihao Hu, Hang Wang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
