Vision-language-action (VLA) robustness is commonly summarized by aggregate task success, which obscures how individual executions change under distribution shifts and where failures emerge in long-horizon tasks. We introduce \textbf{RoboCasa-Shift}, a diagnostic robustness benchmark built on RoboCasa365 that combines...
Hao-Cheng Wang, You-Quan Liu, Wei-Yu Guo et al.· 0 citations
World Action Models (WAMs) jointly predict robot actions and future observations. However, their visual prediction objectives do not explicitly distinguish task-relevant transitions from incidental scene changes. For whole-body policies, this distinction matters because task progress depends on coordinated changes in b...
Yan-Jun Li, Jia-Rui Ye, Wei-Yu Guo et al.· 1 citation
NeuroVLA is introduced, a brain-inspired architecture that couples a cortical vision-language planner to recurrent cerebellar modulation and a stateful spiking spinal controller that translates semantic intent into actions while incorporating high-frequency proprioceptive and force feedback, maintaining short-term moto...
Wei-Yu Guo, He Zhang, Peng-Teng Li et al.· 0 citations
This work proposes DeltaWAM, which jointly predicts visual deltas and actions using dense-anchor, sparse-delta, and action streams, with three architectures that differ in representation and computation sharing, and develops Streaming Delta Memory (SDM), which updates cached anchor context with compact observed deltas,...
Han Yan, Zi-Shang Xiang, Hao-Kai Jiang et al.· 0 citations
This work provides a geometric interpretation of FM uncertainty in the velocity field, showing that uncertainty manifests as deviation from an ideal affine-isotropic contraction field, and introduces denoising acceleration ( accel), a highly-generalizable and cost-free uncertainty proxy that measures the bending of the...
Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sampling may yield diverse behaviors, but users cannot directly choose among valid continuations from the same state. We propose Source-Lifted...
He Zhang, Ying Sun, Pengteng Li et al.· 0 citations
Five representative interfaces are implemented -- discrete state prompt, VLM prefix, action prefix, state expert, and feature modulation -- under matched implementation details, and evaluated on 45 atomic tasks spanning three task families plus 20 composite tasks.
Yiren Zhao, Ziyang Chen, Zi-Yang Rao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.