Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching

原文：Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching

作者：Chenyu Zhang, Yuhang Cao, Daru Du, Yingxi Lu, Jing Shao, Ruoqu Chen, Jiajun Liu, Liu Cao, Yicheng Liu, Hang Zhao, Mengdi Xu

来源：arXiv cs.RO（机器人）

正文

Computer Science > Robotics

arXiv:2609.35469v1 (cs)

[Submitted on 28 Sep 2026]

Title:Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching

Authors:Chenyu Zhang, Yuhang Cao, Daru Du, Yingxi Lu, Jing Shao, Ruoqu Chen, Jiajun Liu, Liu Cao, Yicheng Liu, Hang Zhao, Mengdi Xu

View a PDF of the paper titled Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching, by Chenyu Zhang and 10 other authors

View PDF

HTML (experimental)

Abstract:Autoregressive Vision-Language-Action (VLA) models offer a scalable path to robot learning, yet existing action tokenizers treat tokenization as a compression problem, producing representations that are semantically misaligned with the autoregressive backbone. We propose CATok, a causal action tokenizer that reframes tokenization as a causally structured generative process. CATok introduces a conditional annealing mechanism that extracts action tokens by progressively annealing a flow-matching process: each token is conditioned on all preceding tokens and encodes the residual reconstruction signal at a specific noise level, establishing a coarse-to-fine causal token space whose generative semantics are structurally aligned with autoregressive modeling. A token-conditioned flow-matching decoder built on Multimodal Diffusion Transformer (MMDiT) reconstructs continuous action chunks from these discrete tokens with the precision of hybrid diffusion-head architectures. This discrete bottleneck enforces knowledge insulation by design, cleanly separating high-level semantic reasoning from low-level motor execution without requiring explicit attention masking. Extensive evaluations across three simulation benchmarks and real-world robotic manipulation tasks demonstrate that CATok consistently surpasses existing tokenization methods in both reconstruction fidelity-compression tradeoff and inference efficiency, while improving VLA task success rate and training efficiency, establishing a high-performance, scalable foundation for purely autoregressive VLA systems.

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as:

arXiv:2609.35469 [cs.RO]

(or

arXiv:2609.35469v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.35469

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

机器人 · 人工智能 · 机器学习

由「前沿雷达」于 2026-09-28 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。