arXiv Computer Vision September 25, 2026 By Yufei Duan, Hang Yin, Alberta Longhini, Chao Tang, Danica Kragic

Direction-Scale Decomposition in Action Representation: Rethinking What to Tokenize for Vision-Language-Action Models

Read the original on arXiv Computer Vision →

The paper introduces Direction-Scale Decomposition (DSD), an action representation that separates translation and rotation increments into direction and scale components before tokenization. DSD is evaluated with uniform binning and a B-spline tokenizer (BEAST) in both simulation and real-world manipulation tasks, showing improved success rates on LIBERO and SimplerEnv, especially under mixed-dataset training. Real-robot experiments confirm performance gains with and without robotics pretraining, supporting DSD as an effective representation for discrete-token vision-language-action models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 16

X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining

arXiv:2606. 14752v1 Announce Type: cross Abstract: Modern Vision-Language-Action (VLA) models must bridge pretrained vision-language reasoning and precise continuous robot control.

By Xirui Kang, Yanpei Shi, Lucy Liang, Roy Gan, Dongxiu Liu, Pushi Zhang, Danpeng Chen, Xiaoyi Qin, Yinan Zheng, Jinliang Zheng, Hao Wang, Xianyuan Zhan, Hang Su

nlp robotics efficiency multimodal safety

arXiv AI

Jun 30

SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

arXiv:2606. 30113v1 Announce Type: cross Abstract: Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging.

By Tengyue Jiang, Chunpu Xu, Jiayue Kang, Yao Mu

llms nlp robotics multimodal

arXiv AI

Jun 9

GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation

arXiv:2606. 08530v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments.

By Yuan Zhang, Shiqi Zhang, Yedong Shen, Shuai Dong, Jiajun Deng, Xin Zhang, Yuxuan Gao, Jiajia Wu, Xin Nie, Zhiyuan Cheng, Jianmin Ji, Yanyong Zhang, Xingyi Zhang, Jia Pan

robotics multimodal benchmarks

arXiv Machine Learning

Jul 8

PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

arXiv:2602. 19710v3 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision.

By Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu

nlp robotics multimodal benchmarks safety

arXiv Computer Vision

Aug 31

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

The paper introduces VLAct, a Vision‑Language‑Action model that focuses on representation‑centric continued pre‑training rather than merely scaling robot data. VLAct is trained on diverse, multi‑embodiment robot data and preserves a broad VLM prior while encouraging shared action semantics across embodiments. Experiments across simulation, real‑world, and unseen‑embodiment settings show that VLAct consistently outperforms existing industrial VLA systems, achieving high success rates with only a modest compute budget and open‑source data.

By Senqiao Yang, Chengyao Wang, Yuxin Chen, Zixuan Wang, Longxiang Tang, Haokun Gui, Jinhui Ye, Changsheng Lu, Xiaoyang Wu, Mingkang Zhu, Pengguang Chen, Shu Liu, Zhuotao Tian, Hengshuang Zhao, Bei Yu, Jiaya Jia

robotics fine-tuning multimodal

arXiv Machine Learning

Jul 27

Ordered Action Tokens for Visuomotor Policy Learning

arXiv:2607. 21670v1 Announce Type: cross Abstract: Action tokenization maps continuous robot action chunks to discrete tokens and has become an important interface for modern visuomotor policies.

By Chaoqi Liu, Yue Zhao, Haonan Chen, Xiaoshen Han, Jiawei Gao, Ehsan Adeli, Yilun Du

llms nlp robotics efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining

SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation

PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

Ordered Action Tokens for Visuomotor Policy Learning