Behavior cloning for robot manipulation relies on expert demonstrations. However, for tasks that require dynamic stability, precise contact timing, or dexterous coordination, human operators may find it hard or even impossible to collect data. We study this infeasible-demonstration regime and propose GLIDE: Guardrails...
LLMAE, a method for repurposing a pretrained decoder-only language model as a continuous text autoencoder by exposing the activations of an intermediate layer as a fixed-length latent bottleneck, is proposed and provides an effective substrate for downstream adaptation while benefiting from the fluency of the original...
Arkanath Pathak, Unnat Jain, Alexander C. Berg· 0 citations
TEMPO is proposed, which augments a pretrained VLA with two temporal inputs: a motion summary extracted from a frozen video foundation model to resolve motion ambiguity and a compact proprioceptive history to resolve state aliasing.
Zhen-Yang Feng, Jimin Heo, Erik B. Sudderth et al.· 2 citations· ⚡1
DeVA is introduced, a Decoupled Video-Action model with specialized video and action experts, multi-level feature transfer, and physically salient guidance, enabling rich information exchange while making policy learning more tractable.
Anchor-Align is proposed, which augments BC with two objectives: Vision-Language Anchoring distills layer-wise representations from a frozen VLM copy to prevent this drift, and Language-Action Alignment converts each action target into a discrete motion-direction label and jointly trains language and action prediction...
Applied to two representative VLA systems across simulation benchmarks and real bimanual manipulation tasks, UVT improves training efficiency, final task performance, and policy robustness, with particularly strong gains under limited training budgets and challenging environmental conditions.
Zhen-Yang Feng, Unnat Jain· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
