中文
相关论文

相关论文: LARY: A Latent Action Representation Yielding Benc…

200 篇论文

Vision-Language-Action (VLA) models achieve preliminary generalization through pretraining on large scale robot teleoperation datasets. However, acquiring datasets that comprehensively cover diverse tasks and environments is extremely…

机器人学 · 计算机科学 2026-02-03 Weisheng Dai , Kai Lan , Jianyi Zhou , Bo Zhao , Xiu Su , Junwen Tong , Weili Guan , Shuo Yang

Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy…

机器人学 · 计算机科学 2025-12-22 Jonas Pai , Liam Achenbach , Victoriano Montesinos , Benedek Forrai , Oier Mees , Elvis Nava

Humans can efficiently extract knowledge and learn skills from the videos within only a few trials and errors. However, it poses a big challenge to replicate this learning process for autonomous agents, due to the complexity of visual…

机器学习 · 计算机科学 2025-12-29 Xin Liu , Haoran Li , Dongbin Zhao

World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world models, on the other hand, predict future visual features instead of raw video…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Xinyu Zhang , Zhengtong Xu , Yutian Tao , Yeping Wang , Yu She , Abdeslam Boularias

A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…

机器人学 · 计算机科学 2025-04-28 Shuang Li , Yihuai Gao , Dorsa Sadigh , Shuran Song

Latent Action Models (LAMs) enable learning from actionless data for applications ranging from robotic control to interactive world models. However, existing LAMs typically focus on short-horizon frame transitions and capture low-level…

机器人学 · 计算机科学 2026-03-09 Hanjung Kim , Lerrel Pinto , Seon Joo Kim

Vision-Language-Action (VLA) models empower robots to understand and execute tasks described by natural language instructions. However, a key challenge lies in their ability to generalize beyond the specific environments and conditions they…

The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is…

Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction. Despite their remarkable performance, foundational VLAs are hindered by the…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Zhaoshu Yu , Bo Wang , Pengpeng Zeng , Haonan Zhang , Ji Zhang , Zheng Wang , Lianli Gao , Jingkuan Song , Nicu Sebe , Heng Tao Shen

Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To…

We introduce Being-H0, a dexterous Vision-Language-Action model (VLA) trained on large-scale human videos. Existing VLAs struggle with complex manipulation tasks requiring high dexterity and generalize poorly to novel scenarios and tasks,…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Hao Luo , Yicheng Feng , Wanpeng Zhang , Sipeng Zheng , Ye Wang , Haoqi Yuan , Jiazheng Liu , Chaoyi Xu , Qin Jin , Zongqing Lu

Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Geuntaek Lim , Hyunwoo Kim , Joonsoo Kim , Yukyung Choi

Large-scale visual-language pre-trained models have achieved significant success in various video tasks. However, most existing methods follow an "adapt then align" paradigm, which adapts pre-trained image encoders to model video-level…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Yifei Chen , Dapeng Chen , Ruijin Liu , Sai Zhou , Wenyuan Xue , Wei Peng

Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Junxian Huang , Ruichu Cai , Hao Zhu , Juntao Fang , Boyan Xu , Weilin Chen , Zijian Li , Shenghua Gao

Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains in adapting these models to downstream tasks, especially…

机器人学 · 计算机科学 2025-09-08 Yang Zhang , Chenwei Wang , Ouyang Lu , Yuan Zhao , Yunfei Ge , Zhenglong Sun , Xiu Li , Chi Zhang , Chenjia Bai , Xuelong Li

Learning transferable latent actions from large-scale object manipulation videos can significantly enhance generalization in downstream robotics tasks, as such representations are agnostic to different robot embodiments. Existing approaches…

机器人学 · 计算机科学 2025-12-01 Zuolei Li , Xingyu Gao , Xiaofan Wang , Jianlong Fu

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…

计算机视觉与模式识别 · 计算机科学 2023-03-03 Minghao Chen , Renbo Tu , Chenxi Huang , Yuqi Lin , Boxi Wu , Deng Cai

Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process…

Latent action representations learned from unlabeled videos have recently emerged as a promising paradigm for pretraining vision-language-action (VLA) models without explicit robot action supervision. However, latent actions derived solely…

机器人学 · 计算机科学 2026-04-10 Manish Kumar Govind , Dominick Reilly , Pu Wang , Srijan Das

Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving…

计算机视觉与模式识别 · 计算机科学 2025-04-18 Lan Wang , Yujia Chen , Du Tran , Vishnu Naresh Boddeti , Wen-Sheng Chu