English
Related papers

Related papers: EVA: An Embodied World Model for Future Video Anti…

200 papers

Video Large Language Models (VideoLLMs) excel at video understanding tasks where outputs are textual, such as Video Question Answering and Video Captioning. However, they underperform specialized embedding-based models in Retrieval tasks,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Rohit Gupta , Jayakrishnan Unnikrishnan , Fan Fei , Sheng Liu , Son Tran , Mubarak Shah

Understanding and reasoning over long videos pose significant challenges for large video language models (LVLMs) due to the difficulty in processing intensive video tokens beyond context window and retaining long-term sequential…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Xiaoqian Shen , Wenxuan Zhang , Jun Chen , Mohamed Elhoseiny

This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pretraining methodology. The first stage, Ego-Centric Video…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Yuming Jiang , Siteng Huang , Shengke Xue , Yaxi Zhao , Jun Cen , Sicong Leng , Kehan Li , Jiayan Guo , Kexiang Wang , Mingxiu Chen , Fan Wang , Deli Zhao , Xin Li

We train models to Predict Ego-centric Video from human Actions (PEVA), given the past video and an action represented by the relative 3D body pose. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Yutong Bai , Danny Tran , Amir Bar , Yann LeCun , Trevor Darrell , Jitendra Malik

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…

Robotics · Computer Science 2025-04-28 Shuang Li , Yihuai Gao , Dorsa Sadigh , Shuran Song

We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Yuxin Fang , Wen Wang , Binhui Xie , Quan Sun , Ledell Wu , Xinggang Wang , Tiejun Huang , Xinlong Wang , Yue Cao

Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has…

Embodied Question Answering (EQA) connects perception, reasoning, and interaction within embodied environments. However, existing datasets and benchmarks remain fragmented, each focusing on a limited subset of reasoning skills such as…

Robotics · Computer Science 2026-05-26 Xicheng Gong , Qiwei Li , Peiran Xu , Yadong Mu

Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capture changes in the scene with exceptional temporal…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Song Wu , Zhiyu Zhu , Junhui Hou , Guangming Shi , Jinjian Wu

The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Yaofang Liu , Xiaodong Cun , Xuebo Liu , Xintao Wang , Yong Zhang , Haoxin Chen , Yang Liu , Tieyong Zeng , Raymond Chan , Ying Shan

Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), struggle to cultivate generalizability across diverse…

Robotics · Computer Science 2025-12-04 Yinzhou Tang , Yu Shang , Yinuo Chen , Bingwen Wei , Xin Zhang , Shu'ang Yu , Liangzhi Shi , Chao Yu , Chen Gao , Wei Wu , Yong Li

Embodied world models aim to predict and interact with the physical world through visual observations and actions. However, existing models struggle to accurately translate low-level actions (e.g., joint positions) into precise robotic…

Robotics · Computer Science 2026-04-01 Taiyi Su , Jian Zhu , Yaxuan Li , Chong Ma , Jianjun Zhang , Zitai Huang , Hanli Wang , Yi Xu

In embodied AI, visual perception should be active rather than passive: the system must decide where to look and at what scale to sense to acquire maximally informative data under pixel and spatial budget constraints. Existing vision models…

Robotics · Computer Science 2026-04-06 Jiashu Yang , Yifan Han , Yucheng Xie , Ning Guo , Wenzhao Lian

Generative world models hold significant potential for simulating interactions with visuomotor policies in varied environments. Frontier video models can enable generation of realistic observations and environment interactions in a scalable…

Vision Language Models (VLMs) demonstrate significant potential as embodied AI agents for various mobility applications. However, a standardized, closed-loop benchmark for evaluating their spatial reasoning and sequential decision-making…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Weizhen Wang , Chenda Duan , Zhenghao Peng , Yuxin Liu , Bolei Zhou

AI-driven video analytics has become increasingly important across diverse domains. However, existing systems are often constrained to specific, predefined tasks, limiting their adaptability in open-ended analytical scenarios. The recent…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Yuxuan Yan , Shiqi Jiang , Ting Cao , Yifan Yang , Qianqian Yang , Yuanchao Shu , Yuqing Yang , Lili Qiu

Generative models face a fundamental challenge: they must simultaneously learn high-level semantic concepts (what to generate) and low-level synthesis details (how to generate it). Conventional end-to-end training entangles these distinct,…

Machine Learning · Computer Science 2025-09-30 Deyuan Liu , Peng Sun , Xufeng Li , Tao Lin

World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model Challenge introduces an open-source benchmark of real-world…

Machine Learning · Computer Science 2025-10-09 Riccardo Mereu , Aidan Scannell , Yuxin Hou , Yi Zhao , Aditya Jitta , Antonio Dominguez , Luigi Acerbi , Amos Storkey , Paul Chang

Embodied control requires agents to leverage multi-modal pre-training to quickly learn how to act in new environments, where video demonstrations contain visual and motion details needed for low-level perception and control, and language…

Machine Learning · Computer Science 2023-04-20 Yao Mu , Shunyu Yao , Mingyu Ding , Ping Luo , Chuang Gan

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Yuelin Zhang , Sijie Cheng , Chen Li , Zongzhao Li , Yuxin Huang , Yang Liu , Wenbing Huang