ART is a tool-injection framework that tunes any VLA model to leverage off-the-shelf tool modules for low-level vision, high-level affordance, and embodiment enhancement, and ART reduces the complexity of the action solution space through tool-use, which improves generalizability across different tasks but also reduces...
Ding-Ge Yi, Yanzhao Yu, Xi-Li Dai et al.· 1 citation
In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building interiors. Reliable autonomy remains challenging because robot-terrain interaction (RTI) is hybrid and discontinuous, and effective flipper-track coordination is...
Zhe Gan, Yan-Bo Chen, Li-Rong Che et al.· 0 citations
Retrieve in Time, Correct in Frequency (RTCF), a training-free test-time correction framework that improves frozen VLA performance with low model-side overhead and requires no parameter updates, repeated VLA inference, or additional GPU resources.
Yuze Fan, Yue Cao, Peng-Jie Gao et al.· 0 citations
HerA (Historical Evidence Routing Adapter) is introduced, a framework for routing retained historical evidence into a frozen latent predictor, and RRPM, a lightweight adapter comprising a Structured Memory Bank, Memory Registers, and Workspace Registers support historical evidence routing as a practical adaptation stra...
Yuanruyi, Yue Cao, Hao-Jia Gao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.