Skip to content
conftrace_

action tokenizer

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

vision-language-action model (2) reinforcement learning (2) embodied intelligence (1) embodied artificial intelligence (1) generalist embodied agent (1) vector quantized variational autoencoder (1) zero-shot adaptation (1) cross-domain data (1) generalization performance (1) zero-shot transfer (1)

Papers

MoEActok: A MoE-based Action Tokenizer for Vision-Language-Action Models CVPR 2026 From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons CVPR 2025 VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers ICCV 2025