1 citations · 1 across the 6 of their papers we have counts for
5 papers · 1 filter
CAP: Codebook-Aligned Prediction for Tokenized Robot Policies
Haoran Chen, Jingtian Ji, Samuel Wheeler +2
Action tokenization converts continuous robot actions into discrete symbols that can be modeled autoregressively. However, existing tokenizer-based policies typically ignore the to…
Beyond Reconstruction: What Matters in Action Tokenization for Robot Policies?
Haoran Chen, Jingtian Ji, Samuel Wheeler +2
Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise control actions in continuou…
CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization
Tewodros Ayalew, Matthew Jeung, Samuel Wheeler +5
We introduce CLAW, a fully end-to-end self-supervised framework for learning a world model jointly with continuous latent action representations directly from action-free videos. O…
Mechanistic interpretability for steering vision-language-action models
Bear Häon, Kaylene Stocking, Ian Chuang +1
Vision-Language-Action (VLA) models are a promising path to realizing generalist embodied agents that can quickly adapt to new tasks, modalities, and environments. However, methods…
Discretizing Dynamics for Maximum Likelihood Constraint Inference
Kaylene C. Stocking, David L. McPherson, Robert P. Matthew +1
Maximum likelihood constraint inference is a powerful technique for identifying unmodeled constraints that affect the behavior of a demonstrator acting under a known objective func…