AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

MoEActok: A MoE-based Action Tokenizer for Vision-Language-Action Models

Chunpu Xu, Zhixuan Liang, Tianshuo Yang, Chi-Min Chan, Yang Xiao, Jessie Wang, Xiaokang Yang, Yao Mu

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove pre/post-quantization adapters (ablation)MoEActok · RoboTwin (12 tasks)average success rate: 0.45 -> 0.56Improved
add pre/post-quantization adapters (ablation)MoEActok · Simpler-Env WidowXaverage success rate: 0.17 -> 0.38Improved
add skill-aware VLA training with explicit skill prediction (ablation)MoEActok · RoboTwin (12 tasks)average success rate: 0.47 -> 0.56Improved
add skill-aware VLA training with explicit skill prediction (ablation)MoEActok · Simpler-Env WidowXaverage success rate: 0.30 -> 0.38Improved
increase number of expert quantizers from 1 to 4 (ablation)MoEActok · RoboTwin (12 tasks)average success rate: 0.50 -> 0.56Improved
increase number of expert quantizers from 1 to 4 (ablation)MoEActok · Simpler-Env WidowXaverage success rate: 0.26 -> 0.38Improved
skill-aware training on a single task (ablation)MoEActok · RoboTwin Handover Micsuccess rate: 0.99 -> 0.95No clear effect
use MoEActok instead of VQ-VLA tokenizerVLA with Qwen2.5-0.5B · RoboTwin (12 tasks)average success rate: 0.45 -> 0.56Improved
use MoEActok instead of VQ-VLA tokenizerVLA with Qwen2.5-0.5B · Simpler-Env Stack Green on Yellowsuccess rate: 0.21 -> 0.13Hurt
use MoEActok instead of VQ-VLA tokenizerVLA with Qwen2.5-0.5B · Real robot zero-shot (3 tasks)average success rate: 0.28 -> 0.37Improved
use FAST tokenizer instead of binningVLA with Qwen2.5-0.5B · RoboTwin (12 tasks)average success rate: 0.24 -> 0.17Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy