We have 4 of 30 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Vision-language-action (VLA) models map visual observations and language instructions to continuous robot actions. This task requires a transition from representations that describe the scene and instruction to representations that support action generation. Many continuous-action VLAs leave this transition implicit an...
World action models (WAMs) have advanced robot control by predicting how observations and actions evolve over time. Despite this progress, RGB and action based future prediction does not explicitly address the spatial understanding needed for robot manipulation. Existing efforts often add a limited set of spatial predi...
STAIRCASE POLICY is introduced, a streaming inference and training framework that turns a flow-matching VLA into a JEPA-style WAM and partitions a large action chunk into sub-chunks at staggered denoising stages, enabling long-horizon execution without repeated full policy inference.
The results suggest that current VLA benchmarks may exert limited pressure on deep language grounding and compositional instruction understanding, and that future VLA architectures should allocate capacity more deliberately across language, vision, and action components.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
