English
Related papers

Related papers: The Compression Gap: Why Discrete Tokenization Lim…

200 papers

Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant…

Robotics · Computer Science 2025-12-11 Yifan Ye , Jiaqi Ma , Jun Cen , Zhihe Lu

The existing methods for Vision and Language Navigation in the Continuous Environment (VLN-CE) commonly incorporate a waypoint predictor to discretize the environment. This simplifies the navigation actions into a view selection task and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Yue Zhang , Parisa Kordjamshidi

Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampling every recorded frame as if it provided equally useful supervision. We argue that this…

A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA)…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Jiaming Liu , Hao Chen , Pengju An , Zhuoyang Liu , Renrui Zhang , Chenyang Gu , Xiaoqi Li , Ziyu Guo , Sixiang Chen , Mengzhen Liu , Chengkai Hou , Mengdi Zhao , KC alex Zhou , Pheng-Ann Heng , Shanghang Zhang

Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from above $95\%$ to under $5\%$. Empirical defenses…

Cryptography and Security · Computer Science 2026-05-29 Jianwei Tai

Precision-critical manipulation requires both global trajectory organization and local execution correction, yet most vision-language-action (VLA) policies generate actions within a single unified space. This monolithic formulation forces…

Robotics · Computer Science 2026-04-21 Tingzheng Jia , Kan Guo , Lanping Qian , Yongli Hu , Daxin Tian , Guixian Qu , Chunmian Lin , Baocai Yin , Jiapu Wang

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component…

While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency constraints. Current efforts to mitigate this via token…

Multimedia · Computer Science 2026-03-12 Dongxu Zhang , Yiding Sun , Cheng Tan , Wenbiao Yan , Ning Yang , Jihua Zhu , Haijun Zhang

Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal…

Robotics · Computer Science 2026-03-06 Hugo Buurmeijer , Carmen Amo Alonso , Aiden Swann , Marco Pavone

The advent of Vision-Language-Action (VLA) models represents a significant leap for embodied intelligence, yet their immense computational demands critically hinder deployment on resource-constrained robotic platforms. Intuitively, low-bit…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Yuhao Xu , Yantai Yang , Zhenyang Fan , Yufan Liu , Yuming Li , Bing Li , Zhipeng Zhang

Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Minyoung Lee , Yeji Park , Dongjun Hwang , Yejin Kim , Seong Joon Oh , Junsuk Choe

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Juyi Lin , Amir Taherin , Arash Akbari , Arman Akbari , Lei Lu , Guangyu Chen , Taskin Padir , Xiaomeng Yang , Weiwei Chen , Yiqian Li , Xue Lin , David Kaeli , Pu Zhao , Yanzhi Wang

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations,…

Robotics · Computer Science 2026-05-21 Shizhe Chen , Paul Pacaud , Cordelia Schmid

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by…

Robotics · Computer Science 2025-09-29 Xiaohuan Pei , Yuxing Chen , Siyu Xu , Yunke Wang , Yuheng Shi , Chang Xu

Vision-Language-Action (VLA) models improve action generation by conditioning policies on rich vision-language information. However, current auto-regressive policies are constrained by three bottlenecks: (1) architectural bias drives models…

Robotics · Computer Science 2026-03-31 Yichi Zhang , Weihao Yuan , Yizhuo Zhang , Xidong Zhang , Jia Wan

Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action generation. However, unlike image synthesis where the output spans millions of diverse pixels, a…

Robotics · Computer Science 2026-03-17 Jian Zhou , Sihao Lin , Shuai Fu , Zerui Li , Gengze Zhou , Qi WU

While vision-language-action (VLA) models have shown great promise for robot manipulation, their deployment on rigid industrial robots remains challenging due to the inherent trade-off between compliance and responsiveness. Standard…

Robotics · Computer Science 2026-03-18 Johannes Hechtl , Philipp Schmitt , Georg von Wichert , Wolfram Burgard

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling,…

Robotics · Computer Science 2026-04-01 Weiqi Li , Quande Zhang , Ruifeng Zhai , Liang Lin , Guangrun Wang

Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities. This paper revisits a…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Jianke Zhang , Xiaoyu Chen , Qiuyue Wang , Mingsheng Li , Yanjiang Guo , Yucheng Hu , Jiajun Zhang , Shuai Bai , Junyang Lin , Jianyu Chen

Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Phat Nguyen , Ngai-Man Cheung