Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.
In-context learning enables robot action prediction in llms
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
Decompose and Recompose decomposes seen robotic demonstrations into skill-action alignments and recomposes them via visual-semantic retrieval and planning to enable zero-shot cross-task generalization.
Steerable VLAs trained on rich synthetic commands at subtask, motion, and pixel levels enable VLMs to steer robot behavior more effectively, outperforming prior hierarchical baselines on real-world manipulation and generalization tasks.
citing papers explorer
-
Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation
Decompose and Recompose decomposes seen robotic demonstrations into skill-action alignments and recomposes them via visual-semantic retrieval and planning to enable zero-shot cross-task generalization.