AI Paper Atlas

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

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

Yating Wang, Haoyi Zhu, Mingyu Liu, Jiange Yang, Hao-Shu Fang, Tong He

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 48 citations (OpenAlex)

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
replace OpenVLA action tokens with Residual VQ-VAE tokenizer (trained on ManiSkill+RLBench)OpenVLA · LIBERO-90success rate (%): 73.53 -> 80.98Improved
train tokenizer on ManiSkill only instead of ManiSkill+RLBench (ablation)VQ-VLA tokenizer · LIBERO-90success rate (%): 80.98 -> 14.38Hurt
use temporal conv encoder/decoder instead of MLP (ablation)Residual VQ-VAE · LIBERO-10success rate (%): 53.4 -> 60.0Improved
use temporal conv instead of MLP (ablation)Residual VQ-VAE · LIBERO-GOALsuccess rate (%): 72.6 -> 75.2Improved
train tokenizer on all LIBERO instead of LIBERO-10 only (ablation)Conv Residual VQ-VAE · LIBERO-10success rate (%): 54.0 -> 60.0Improved
train tokenizer on all LIBERO instead of LIBERO-GOAL only (ablation)Conv Residual VQ-VAE · LIBERO-GOALsuccess rate (%): 72.4 -> 75.2Improved
add ManiSkill synthetic data to tokenizer training (ablation)VQ_O+L · Real-world: Flip the pot uprightsuccess rate (%): 45.0 -> 60.0Improved
add ManiSkill synthetic data to tokenizer training (ablation)VQ_O+L · Real-world: Put the toy into the drawersuccess rate (%): 10.0 -> 25.0Improved
add LIBERO data to tokenizer training (VQ_O to VQ_O+L) (ablation)VQ-VLA · Real-world short-horizon tasksaverage success rate (%): increased by only 0.5%No clear effect
train tokenizer on LIBERO only (VQ_L) vs real+LIBERO (ablation)VQ-VLA · Real-world taskssuccess rate (%): 55.0 vs 45.0 (Flip pot)No clear effect
use VQ-based action chunking instead of autoregressive chunking (ablation)OpenVLA · LIBERO-90success rate (%): 66.53 -> 86.61Improved
use autoregressive 5-action chunking in OpenVLA (ablation)OpenVLA · Real-world: Put the toy into the basketsuccess rate (%): 20.0 -> 0.0Hurt

Later papers that compared with this method

2 later accepted papers report VQ-VLA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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