English
Related papers

Related papers: Scaling Autoregressive Video Models

200 papers

We propose Heterogeneous Masked Autoregression (HMA) for modeling action-video dynamics to generate high-quality data and evaluation in scaling robot learning. Building interactive video world models and policies for robotics is difficult…

Robotics · Computer Science 2025-02-07 Lirui Wang , Kevin Zhao , Chaoqi Liu , Xinlei Chen

Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement,…

Robotics · Computer Science 2025-08-27 Nicholas Pfaff , Hongkai Dai , Sergey Zakharov , Shun Iwase , Russ Tedrake

Collecting high-quality data for training large-scale robotic models typically relies on real robot platforms, which is labor-intensive and costly, whether via teleoperation or scripted demonstrations. To scale data collection, many…

Robotics · Computer Science 2025-12-02 X. Hu , G. Ye

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

Computer Vision and Pattern Recognition · Computer Science 2019-09-19 C. Spampinato , S. Palazzo , P. D'Oro , D. Giordano , M. Shah

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Xun Huang , Zhengqi Li , Guande He , Mingyuan Zhou , Eli Shechtman

Generative models have emerged as an essential building block for many image synthesis and editing tasks. Recent advances in this field have also enabled high-quality 3D or video content to be generated that exhibits either multi-view or…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Sherwin Bahmani , Jeong Joon Park , Despoina Paschalidou , Hao Tang , Gordon Wetzstein , Leonidas Guibas , Luc Van Gool , Radu Timofte

Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation methods, often distilled from a corresponding many-step…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jiaqi Feng , Justin Cui , Yuanhao Ban , Cho-Jui Hsieh

Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cost of collecting diverse demonstrations, particularly for…

Robotics · Computer Science 2026-03-24 Yujie Zhao , Hongwei Fan , Di Chen , Shengcong Chen , Liliang Chen , Xiaoqi Li , Guanghui Ren , Hao Dong

Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos. However, they often generate clips based on static prompts (e.g., text or images),…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Haoran He , Yang Zhang , Liang Lin , Zhongwen Xu , Ling Pan

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Sucheng Ren , Chen Chen , Zhenbang Wang , Liangchen Song , Xiangxin Zhu , Alan Yuille , Yinfei Yang , Jiasen Lu

We show that useful video representations can be learned from synthetic videos and natural images, without incorporating natural videos in the training. We propose a progression of video datasets synthesized by simple generative processes,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Xueyang Yu , Xinlei Chen , Yossi Gandelsman

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Tianwei Xiong , Jun Hao Liew , Zilong Huang , Jiashi Feng , Xihui Liu

Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with the rapid expansion of online video. Over the past six years, research has produced…

Autoregressive video diffusion models generate streaming video by producing frames sequentially, conditioning each chunk on previously generated content. These models are structurally anchored to the first frame: its key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yusuf Dalva , Pinar Yanardag

Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Samuel Garcin , Thomas Walker , Steven McDonagh , Tim Pearce , Hakan Bilen , Tianyu He , Kaixin Wang , Jiang Bian

Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Honghui Yang , Di Huang , Wei Yin , Chunhua Shen , Haifeng Liu , Xiaofei He , Binbin Lin , Wanli Ouyang , Tong He

Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Nick Stracke , Kolja Bauer , Stefan Andreas Baumann , Miguel Angel Bautista , Josh Susskind , Björn Ommer

Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Weijia Wu , Mingyu Liu , Zeyu Zhu , Xi Xia , Haoen Feng , Wen Wang , Kevin Qinghong Lin , Chunhua Shen , Mike Zheng Shou

We address the problem of detecting attention targets in video. Our goal is to identify where each person in each frame of a video is looking, and correctly handle the case where the gaze target is out-of-frame. Our novel architecture…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Eunji Chong , Yongxin Wang , Nataniel Ruiz , James M. Rehg

With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the two most common…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Ali Abdari , Pouria Amirjan , Azadeh Mansouri