Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fine-tuning works against that promise. A vision-language-action model trained to solve one task distribution concentrates its flow-matching decoder around the dominant dem...
Chen Zhao, Zi-Peng Ye, Hai-Tao Shen et al.· 0 citations
Cross-task generalization remains difficult for world action models (WAMs), even when their predicted futures depict plausible manipulation. This gap can be attributed directly: we make this gap directly testable by decoupling a WAM into a world model and an inverse-dynamics model (IDM), then holding the IDM fixed whil...
Chen Zhao, Zi-Peng Ye, Yi-Han Lin et al.· 0 citations
Achieving robust cross-embodiment generalization in imitation learning demands overcoming a critical representation flaw that inextricably entangles task semantics with hardware-specific visual geometry. We propose an interaction-centric framework that leverages the shared structure of two-finger grippers via a paramet...
Guan-Lin Li, Shi-Feng Bao, Yi-Han Zhao et al.· 0 citations
RoboHarn-Evo is introduced, a dual-loop harness that evolves Hierarchical Physical Knowledge (HPK) from physical experience that demonstrates that physical interaction can be accumulated into reusable knowledge for improving subsequent manipulation.
Shi-Feng Bao, Fan-Ding Huang, Yi-Han Lin et al.· 2 citations
Results show that initial-state performance does not determine recovery performance and policies exhibit different recovery strengths across scenarios, and RoboRecover establishes recovery from execution-induced intermediate states as a distinct dimension of robot policy evaluation.
Yang Li, Chen Zhao, Zhuo-Ran Wang et al.· 1 citation
This work introduces HASP (Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs) that act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.
JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor, predicts a spatially structured joint current-future target that captures task-shared visual temporal structure between current and future observations, whi...
Yi-Han Lin, Jia-Wei He, Shi-Feng Bao et al.· 12 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
