中文
相关论文

相关论文: CAST: Counterfactual Labels Improve Instruction Fo…

200 篇论文

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…

机器人学 · 计算机科学 2026-03-31 Yichi Zhang , Weihao Yuan , Yizhuo Zhang , Xidong Zhang , Jia Wan

We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require…

In recent years, Vision-Language-Action (VLA) models have become a vital research direction in robotics due to their impressive multimodal understanding and generalization capabilities. Despite the progress, their practical deployment is…

机器人学 · 计算机科学 2025-06-17 Wenxuan Song , Jiayi Chen , Pengxiang Ding , Yuxin Huang , Han Zhao , Donglin Wang , Haoang Li

Language-conditioned policies have recently gained substantial adoption in robotics as they allow users to specify tasks using natural language, making them highly versatile. While much research has focused on improving the action…

机器人学 · 计算机科学 2025-04-25 Eugenio Chisari , Jan Ole von Hartz , Fabien Despinoy , Abhinav Valada

Vision-Language-Action (VLA) models have shown strong performance on embodied manipulation, yet they remain brittle under visual observation changes, paraphrased language instructions, and compounded perturbations. This limitation suggests…

机器人学 · 计算机科学 2026-05-20 Jingzhou Luo , Yifan Wen , Yongjie Bai , Xinshuai Song , Yang Liu , Liang Lin

The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large…

机器人学 · 计算机科学 2023-10-27 Huihan Liu , Alice Chen , Yuke Zhu , Adith Swaminathan , Andrey Kolobov , Ching-An Cheng

The reliance on language in Vision-Language-Action (VLA) models introduces ambiguity, cognitive overhead, and difficulties in precise object identification and sequential task execution, particularly in environments with multiple visually…

机器人学 · 计算机科学 2026-03-02 Donggeon Kim , Seungwon Jan , Hyeonjun Park , Daegyu Lim

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…

计算机视觉与模式识别 · 计算机科学 2025-10-03 Angen Ye , Zeyu Zhang , Boyuan Wang , Xiaofeng Wang , Dapeng Zhang , Zheng Zhu

To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specific data. However, since this recipe updates existing representations, it is unsuitable for…

机器人学 · 计算机科学 2026-05-18 Ralf Römer , Yi Zhang , Yuming Li , Angela P. Schoellig

The rapid advancement of generative AI and multi-modal foundation models has shown significant potential in advancing robotic manipulation. Vision-language-action (VLA) models, in particular, have emerged as a promising approach for…

软件工程 · 计算机科学 2025-05-13 Zhijie Wang , Zhehua Zhou , Jiayang Song , Yuheng Huang , Zhan Shu , Lei Ma

Vision-Language-Action (VLA) models have recently made significant advance in multi-task, end-to-end robotic control, due to the strong generalization capabilities of Vision-Language Models (VLMs). A fundamental challenge in developing such…

机器人学 · 计算机科学 2025-06-17 Yuqing Wen , Kefan Gu , Haoxuan Liu , Yucheng Zhao , Tiancai Wang , Haoqiang Fan , Xiaoyan Sun

In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning…

计算机视觉与模式识别 · 计算机科学 2024-05-10 Junsu Kim , Yunhoe Ku , Jihyeon Kim , Junuk Cha , Seungryul Baek

Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…

机器人学 · 计算机科学 2025-05-27 Guanxing Lu , Wenkai Guo , Chubin Zhang , Yuheng Zhou , Haonan Jiang , Zifeng Gao , Yansong Tang , Ziwei Wang

Vision Language Action (VLA) models represent a transformative shift in robotics, with the aim of unifying visual perception, natural language understanding, and embodied control within a single learning framework. This review presents a…

机器人学 · 计算机科学 2026-01-21 Muhayy Ud Din , Waseem Akram , Lyes Saad Saoud , Jan Rosell , Irfan Hussain

Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals…

计算与语言 · 计算机科学 2026-04-15 Qingyu Ren , Qianyu He , Powei Chang , Jie Zeng , Zeye Sun , Fei Yu , Jiaqing Liang , Yanghua Xiao

Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing…

密码学与安全 · 计算机科学 2025-11-18 Jiayu Li , Yunhan Zhao , Xiang Zheng , Zonghuan Xu , Yige Li , Xingjun Ma , Yu-Gang Jiang

Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Yifan Li , Yikai Wang , Yanwei Fu , Dongyu Ru , Zheng Zhang , Tong He

Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world…

机器人学 · 计算机科学 2026-05-26 Xiaokang Liu , Zechen Bai , Hai Ci , Kevin Yuchen Ma , Mike Zheng Shou

Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation by grounding high-level semantic instructions into executable physical actions. However, prevailing approaches typically adopt a monolithic…

机器人学 · 计算机科学 2026-04-29 Yifei Wei , Linqing Zhong , Yi Liu , Yuxiang Lu , Xindong He , Maoqing Yao , Guanghui Ren

The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for…

机器学习 · 计算机科学 2025-10-30 Nikita Kachaev , Mikhail Kolosov , Daniil Zelezetsky , Alexey K. Kovalev , Aleksandr I. Panov