Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915929319800832 |
|---|---|
| author | Liang, Yuanchang Wang, Xiaobo Wang, Kai Wang, Shuo Peng, Xiaojiang Chen, Haoyu Chua, David Kim Huat Vadakkepat, Prahlad |
| author_facet | Liang, Yuanchang Wang, Xiaobo Wang, Kai Wang, Shuo Peng, Xiaojiang Chen, Haoyu Chua, David Kim Huat Vadakkepat, Prahlad |
| contents | In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique to improve robotic manipulation abilities. However, a large chunk size reduces the model's responsiveness to new information, while a small one increases the likelihood of mode-jumping, jerky behavior resulting from discontinuities between chunks. Therefore, selecting the optimal chunk size is an urgent demand to balance the model's reactivity and consistency. Unfortunately, a dominant trend in current VLA models is an empirical fixed chunk length at inference-time, hindering their superiority and scalability across diverse manipulation tasks. To address this issue, we propose a novel Adaptive Action Chunking (AAC) strategy, which exploits action entropy as the cue to adaptively determine the chunk size based on current predictions. Extensive experiments on a wide range of simulated and real-world robotic manipulation tasks have demonstrated that our approach substantially improves performance over the state-of-the-art alternatives. The videos and source code are publicly available at https://lance-lot.github.io/adaptive-chunking.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04161 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Action Chunking at Inference-time for Vision-Language-Action Models Liang, Yuanchang Wang, Xiaobo Wang, Kai Wang, Shuo Peng, Xiaojiang Chen, Haoyu Chua, David Kim Huat Vadakkepat, Prahlad Robotics In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique to improve robotic manipulation abilities. However, a large chunk size reduces the model's responsiveness to new information, while a small one increases the likelihood of mode-jumping, jerky behavior resulting from discontinuities between chunks. Therefore, selecting the optimal chunk size is an urgent demand to balance the model's reactivity and consistency. Unfortunately, a dominant trend in current VLA models is an empirical fixed chunk length at inference-time, hindering their superiority and scalability across diverse manipulation tasks. To address this issue, we propose a novel Adaptive Action Chunking (AAC) strategy, which exploits action entropy as the cue to adaptively determine the chunk size based on current predictions. Extensive experiments on a wide range of simulated and real-world robotic manipulation tasks have demonstrated that our approach substantially improves performance over the state-of-the-art alternatives. The videos and source code are publicly available at https://lance-lot.github.io/adaptive-chunking.github.io/. |
| title | Adaptive Action Chunking at Inference-time for Vision-Language-Action Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.04161 |