Codebook-Aligned Prediction (CAP) is introduced, a method that directly reuses the tokenizer's code vectors as policy class prototypes while leaving the tokenizer and policy backbone otherwise unchanged, suggesting that action tokenizers learn useful action-aware latent structure beyond discrete targets that should be preserved when training downstream policies.
Abstract
Action tokenization converts continuous robot actions into discrete symbols that can be modeled autoregressively. However, existing tokenizer-based policies typically ignore the tokenizer's learned latent code structure: after tokenization, the policy treats tokens as unrelated class indices and learns a new classifier from scratch. We show that this discarded structure is valuable. We introduce Codebook-Aligned Prediction (CAP), a method that directly reuses the tokenizer's code vectors as policy class prototypes while leaving the tokenizer and policy backbone otherwise unchanged. Across four quantizer families, three simulation benchmarks, and two real-robot tasks, CAP consistently improves task success over standard token classification heads while holding the tokenizer (and therefore its reconstruction quality) fixed. Our analysis further shows that these gains are not explained by higher token accuracy or changes in the policy head alone. Instead, reusing the tokenizer codebook provides the policy with valuable information about the tokenizer's learned latent structure across tokens, making token prediction errors more benign in action space and improving the representations learned by the policy backbone. These results suggest that action tokenizers learn useful action-aware latent structure beyond discrete targets that should be preserved when training downstream policies.
Autoregressive robot policies rely on action tokenizers to convert continuous action chunks into compact sequences of discrete prediction targets. Existing tokenizers can reconstruct action chunks from discrete codes, but often leave implicit what each individual token contributes to the reconstructed action. We introd...
Di-Jia Zhan, Zhuo-Wen Li, Xue-Miao Xu et al.· 0 citations
Autoregressive robot policies learn continuous control by predicting discrete action tokens from observations. Different tasks often share local motions, yet behavioral correspondence across demonstrations receives limited explicit supervision in existing tokenizers. Motions with different timing can therefore lack a s...
Ju Dong, Ze Chen, Zhen-Dong Xie et al.· arXiv.org· 1 citation· ⚡1
Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise control actions in continuous space. Many action tokenizers learn the mapping between tokens and actions via a reconstruction objective. However, as we show through ext...
Hao-Ran Chen, Jing-Tian Ji, S. Wheeler et al.· 1 citation
TOkenization of Action sequences with STochastic sampling (TOAST), a stochastic action tokenization method that samples alternative tokenizations of the same quantized action sequence during policy training, demonstrates the effectiveness of stochastic action tokenization for autoregressive robot policy learning, parti...
Keisuke Shirai, Tomohiro Motoda, Hanbit Oh et al.· 0 citations
On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals. Its sampled-token variant avoids the cost of full-vocabulary probabilities. Yet we find that training on fewer tokens can outperform full-token OPD, challenging the intuition that more supervision improves learning....
An-Hao Zhao, Hao-Ran Xin, Jun-Long Tong et al.· 0 citations
Vision-language-action (VLA) policies have demonstrated strong generalization in robotic manipulation, yet processing dense visual tokens often incurs high inference latency. Visual token pruning offers a practical way to reduce this cost, but identifying a compact set of tokens that preserves reliable action generatio...
Xiao-Yang Xing, Chun-Mei Feng, A. Cohn 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.