Cover Image

The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Shiba, Takuya
Format:	Preprint
Published:	2026
Subjects:	Robotics Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
by: Liang, Zhixuan, et al.
Published: (2025)

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
by: Xu, Siyu, et al.
Published: (2025)

LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
by: Hou, Yuchen, et al.
Published: (2026)

Tactile Modality Fusion for Vision-Language-Action Models
by: Morissette, Charlotte, et al.
Published: (2026)

PVI: Plug-in Visual Injection for Vision-Language-Action Models
by: Zhang, Zezhou, et al.
Published: (2026)

Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
by: Guruprasad, Pranav, et al.
Published: (2024)

Improving Vision-Language-Action Model with Online Reinforcement Learning
by: Guo, Yanjiang, et al.
Published: (2025)

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
by: Luo, Hao, et al.
Published: (2025)

Test-Time Training for Visual Foresight Vision-Language-Action Models
by: Park, Sangwu, et al.
Published: (2026)

TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models
by: Liu, Chenghao, et al.
Published: (2025)

PointVLA: Injecting the 3D World into Vision-Language-Action Models
by: Li, Chengmeng, et al.
Published: (2025)

Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models
by: Bendikas, Rokas, et al.
Published: (2025)

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model
by: Zhou, Zhongyi, et al.
Published: (2025)

Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
by: Lin, Haitao, et al.
Published: (2026)

Hybrid Training for Vision-Language-Action Models
by: Mazzaglia, Pietro, et al.
Published: (2025)

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models
by: An, Xinyuan, et al.
Published: (2026)

GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
by: Cheang, Chi-Lam, et al.
Published: (2024)

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
by: Xiao, Lei, et al.
Published: (2025)

A Survey on Efficient Vision-Language-Action Models
by: Yu, Zhaoshu, et al.
Published: (2025)

Interactive Post-Training for Vision-Language-Action Models
by: Tan, Shuhan, et al.
Published: (2025)

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
by: Wang, Yating, et al.
Published: (2025)

UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation
by: Sautenkov, Oleg, et al.
Published: (2025)

From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
by: Zhang, Zhengshen, et al.
Published: (2025)

Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
by: Gao, Juntao, et al.
Published: (2025)

Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
by: Grover, Shresth, et al.
Published: (2025)

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
by: Kim, Moo Jin, et al.
Published: (2025)

LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning
by: Niu, Dantong, et al.
Published: (2024)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
by: Zhao, Qingqing, et al.
Published: (2025)

Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
by: Taherin, Amir, et al.
Published: (2025)

Automated Data Curation Using GPS & NLP to Generate Instruction-Action Pairs for Autonomous Vehicle Vision-Language Navigation Datasets
by: Roque, Guillermo, et al.
Published: (2025)

EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
by: Yang, Ruihan, et al.
Published: (2025)

Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
by: Kawaharazuka, Kento, et al.
Published: (2025)

Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
by: He, Haoran, et al.
Published: (2024)

FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
by: Liu, Yicheng, et al.
Published: (2025)

MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models
by: Zhou, Xunlan, et al.
Published: (2026)

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
by: Zhao, Yanpeng, et al.
Published: (2026)

VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models
by: Chen, Yiye, et al.
Published: (2026)

MResT: Multi-Resolution Sensing for Real-Time Control with Vision-Language Models
by: Saxena, Saumya, et al.
Published: (2024)

Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models
by: Lee, Seungjae, et al.
Published: (2025)

AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
by: Xing, Shuo, et al.
Published: (2024)