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

Chun-Pu Xu Zhi-Xuan Liang Tianshuo Yang Chi-Min Chan Yang Xiao Jessie Wang Xiao-Kang Yang Yao Mu PolyU Sjtu Shanghai AI Laboratory Hku Hkust

· 1 citation · 33 references

TL;DR

Across both simulated and real-world settings, MoEActok-based VLA substantially outperforms existing VLA models in both simulated and real-world settings.

Semantic Scholar

View source

Similar papers

Preprint Sep 2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

IMLE-VLA is introduced, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE), and promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely.

Kian Hosseinkhani, Qin-He Peng, George Shramko et al. · 1 citation

Preprint Oct 2026

VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding

Pretrained vision-language models (VLMs) already exhibit strong visual, spatial and reasoning capabilities relevant to robotic manipulation. The key challenge in turning pretrained VLMs into generalist manipulation policies is to expose these capabilities through an appropriate action interface. Vision-language-action...

Jing-Kun Yi, Shu-Jie Zhang, Zi-Rui Zhou et al. · 0 citations

Preprint Oct 2026

CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation

Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (AE) poses a key challenge for low-bit post-training quantization (PTQ). The AE is repeatedly invoked across denoising steps and policy queries, where fixed calibration...

Jin Hyun, Jung Gyu Min, Gyuhyun Jung et al. · 0 citations

Preprint Sep 2026

ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models

Results indicate that a fixed VLA policy can benefit from conditioning on spatiotemporally aligned demonstrations at test time, and present ICI-VLA, a training and retrieval framework that equips a text-action VLM with few-shot test-time adaptation through in-context demonstrations.

Song-Hua Yang, Zi-Yu Liu, Xue-Tao Li et al. · 0 citations

Preprint Oct 2026

StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models

Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These action heads typically process the denoising trajectory in a largely uniform manner. However, we observe that the conditioning focus naturally shifts across denoising stage...

Shang-Yuan Yuan, Xin-Da Qi, Yu-Jiang Pu et al. · 0 citations

Preprint Oct 2026

Juno: Taming Predictive Latents for Vision-Language-Action Models

Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predictive latents for vision-language-action (VLA) models. Yet making these latents useful across pretraining, policy learning, and deployment requires addressing three failures:...

Yu-Chen Zhu, Chen-Yi Xu, Yu-Lin Zhang et al. · 0 citations