English
Related papers

Related papers: Unified Video Action Model

200 papers

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…

Robotics · Computer Science 2025-12-01 Zuolei Li , Xingyu Gao , Xiaofan Wang , Jianlong Fu

Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or behavioral distribution shifts, and their performance is…

Robotics · Computer Science 2025-08-04 Junbang Liang , Pavel Tokmakov , Ruoshi Liu , Sruthi Sudhakar , Paarth Shah , Rares Ambrus , Carl Vondrick

Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Fuxiang Yang , Donglin Di , Lulu Tang , Xuancheng Zhang , Lei Fan , Hao Li , Chen Wei , Tonghua Su , Baorui Ma

In recent years, video action recognition, as a fundamental task in the field of video understanding, has been deeply explored by numerous researchers.Most traditional video action recognition methods typically involve converting videos…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Junlin Chen , Chengcheng Xu , Yangfan Xu , Jian Yang , Jun Li , Zhiping Shi

We present a unified network for simultaneously generating videos and their corresponding entity segmentation and depth maps from text prompts. We utilize colormap to represent entity masks and depth maps, tightly integrating dense…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Lehan Yang , Lu Qi , Xiangtai Li , Sheng Li , Varun Jampani , Ming-Hsuan Yang

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained…

Robotics · Computer Science 2025-12-09 Yichao Shen , Fangyun Wei , Zhiying Du , Yaobo Liang , Yan Lu , Jiaolong Yang , Nanning Zheng , Baining Guo

Bimanual manipulation is crucial in robotics, enabling complex tasks in industrial automation and household services. However, it poses significant challenges due to the high-dimensional action space and intricate coordination requirements.…

Predictive foresight is important to intelligent embodied agents. Since the motor execution of a robot is intrinsically constrained by its visual perception of environmental geometry, effectively anticipating the future requires capturing…

Robotics · Computer Science 2026-03-12 Xiaoxu Xu , Hao Li , Jinhui Ye , Yilun Chen , Jia Zeng , Xinyi Chen , Linning Xu , Dahua Lin , Weixin Li , Jiangmiao Pang

Pretrained video generation models provide strong priors for robot control, but existing unified world action models still struggle to decode reliable actions without substantial robot-specific training. We attribute this limitation to a…

Robotics · Computer Science 2026-04-14 Liaoyuan Fan , Zetian Xu , Chen Cao , Wenyao Zhang , Mingqi Yuan , Jiayu Chen

In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip…

Computer Vision and Pattern Recognition · Computer Science 2020-12-16 Xinyu Li , Chunhui Liu , Bing Shuai , Yi Zhu , Hao Chen , Joseph Tighe

Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zhiyu Tan , Hao Yang , Luozheng Qin , Jia Gong , Mengping Yang , Hao Li

Vision-Language-Action (VLA) models aim to control robots for manipulation from visual observations and natural-language instructions. However, existing hierarchical and autoregressive paradigms often introduce architectural overhead,…

Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs, typically relying on either slow multi-step video generation…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Haodong Yan , Zhide Zhong , Jiaguan Zhu , Junjie He , Weilin Yuan , Wenxuan Song , Xin Gong , Yingjie Cai , Guanyi Zhao , Xu Yan , Bingbing Liu , Ying-Cong Chen , Haoang Li

Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of latent intentions to predict upcoming actions. Existing transformer-based approaches, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Tsung-Ming Tai , Sofia Casarin , Andrea Pilzer , Werner Nutt , Oswald Lanz

Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under…

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…

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yian Zhao , Feng Wang , Qiushan Guo , Chang Liu , Xiangyang Ji , Jian Zhang , Jie Chen

In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions and for enabling robotic planning. However, existing paradigms fall short of jointly modeling these…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Binjie Zhang , Mike Zheng Shou

VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Yecheng Wu , Zhuoyang Zhang , Junyu Chen , Haotian Tang , Dacheng Li , Yunhao Fang , Ligeng Zhu , Enze Xie , Hongxu Yin , Li Yi , Song Han , Yao Lu

We present a method to generate video-action pairs that follow text instructions, starting from an initial image observation and the robot's joint states. Our approach automatically provides action labels for video diffusion models,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Liudi Yang , Yang Bai , George Eskandar , Fengyi Shen , Mohammad Altillawi , Dong Chen , Ziyuan Liu , Abhinav Valada