In embodied manipulation, Vision Language Action (VLA) models can execute atomic skills, but long-horizon manipulation requires recombining these skills without demonstrations for every skill combination. The full instruction route treats skill chaining as long-horizon imitation. In a controlled study, full instruction...
Xu-Peng Zhang, Yan-Tai Yang, Chang Guo et al.· 0 citations
This work introduces a VLA tool-family interface that exposes explicit tool selection and in-execution progress feedback, enabling efficient event-triggered agent replanning without continuous agent polling and proposes Tool-Aligned Post-Training (TAPT), which constructs invocation-aligned training units for instructio...
This work introduces RoboFollow, a diagnostic benchmark with three principles, which exposes genuine instruction following as a critical, overlooked bottleneck in embodied agents' ability to follow instructions.
Chang Guo, Yu-Kun Xie, Bo-Han Tan et al.· 0 citations
Libra is presented, which operationalizes the law of large numbers (LLN) as a scaling principle for load balancing: the attention-balancing pool need not grow with the DP degree.
Yan Wang, Xiu-Long Yuan, Kaiming Yang et al.· arXiv.org· 1 citation
This work demonstrates that robust semantic grounding can be achieved through elegant structural design, bypassing the inefficient brute-force data scaling paradigm and introduces ParaVLA, a natively decoupled 0.33B-parameter model exhibiting near-perfect robustness to instruction rewording.
Zhao-Kai Yin, Zhi-Peng Zhang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
