English
Related papers

Related papers: DySink: Dynamic Frame Sinks for Autoregressive Lon…

200 papers

We address the problem of generating long-horizon videos for robotic manipulation tasks. Text-to-video diffusion models have made significant progress in photorealism, language understanding, and motion generation but struggle with…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Liudi Yang , Yang Bai , George Eskandar , Fengyi Shen , Mohammad Altillawi , Dong Chen , Soumajit Majumder , Ziyuan Liu , Gitta Kutyniok , Abhinav Valada

Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong…

Machine Learning · Computer Science 2025-03-04 Xingzhuo Guo , Yu Zhang , Baixu Chen , Haoran Xu , Jianmin Wang , Mingsheng Long

We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Huan Cui , Qing Li , Hanling Wang , Yong jiang

Talking head generation intends to produce vivid and realistic talking head videos from a single portrait and speech audio clip. Although significant progress has been made in diffusion-based talking head generation, almost all methods rely…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Hanbo Cheng , Limin Lin , Chenyu Liu , Pengcheng Xia , Pengfei Hu , Jiefeng Ma , Jun Du , Jia Pan

Current autoregressive video diffusion models are constrained by three core bottlenecks: (i) the finite temporal horizon imposed by the base model's 3D Rotary Positional Embedding (3D-RoPE), (ii) slow prompt responsiveness in maintaining…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Hidir Yesiltepe , Tuna Han Salih Meral , Adil Kaan Akan , Kaan Oktay , Pinar Yanardag

Autoregressive models (ARMs) and diffusion models (DMs) represent two leading paradigms in generative modeling, each excelling in distinct areas: ARMs in global context modeling and long-sequence generation, and DMs in generating…

Machine Learning · Computer Science 2024-10-08 Hyungjin Chung , Dohun Lee , Jong Chul Ye

Current autoregressive diffusion models excel at video generation but are generally limited to short temporal durations. Our theoretical analysis indicates that the autoregressive modeling typically suffers from temporal drift caused by…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Xunzhi Xiang , Yabo Chen , Guiyu Zhang , Zhongyu Wang , Zhe Gao , Quanming Xiang , Gonghu Shang , Junqi Liu , Haibin Huang , Yang Gao , Chi Zhang , Qi Fan , Xuelong Li

AI-generated content has attracted lots of attention recently, but photo-realistic video synthesis is still challenging. Although many attempts using GANs and autoregressive models have been made in this area, the visual quality and length…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Yingqing He , Tianyu Yang , Yong Zhang , Ying Shan , Qifeng Chen

Generating long videos using pre-trained video diffusion models, which are typically trained on short clips, presents a significant challenge. Directly applying these models for long-video inference often leads to a notable degradation in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jiahao Tian , Chenxi Song , Wei Cheng , Chi Zhang

Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. However, due to the bidirectional attention mechanism, DLMs incur substantial computational cost as context length…

Computation and Language · Computer Science 2026-01-07 Yang Li , Han Meng , Chenan Wang , Haipeng Chen

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mingqiang Wu , Weilun Feng , Zhefeng Zhang , Haotong Qin , Yuqi Li , Guoxin Fan , Xiaokun Liu , Zhulin An , Libo Huang , Yongjun Xu , Chuanguang Yang

Interactive long video generation requires prompt switching to introduce new subjects or events, while maintaining perceptual fidelity and coherent motion over extended horizons. Recent distilled streaming video diffusion models reuse a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yang Yang , Tianyi Zhang , Wei Huang , Jinwei Chen , Boxi Wu , Xiaofei He , Deng Cai , Bo Li , Peng-Tao Jiang

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

Computation and Language · Computer Science 2026-04-07 Oshri Naparstek

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Yixuan Pei , Zhiwu Qing , Jun Cen , Xiang Wang , Shiwei Zhang , Yaxiong Wang , Mingqian Tang , Nong Sang , Xueming Qian

We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. FramePack compresses input frame contexts with frame-wise importance so that more frames can be encoded…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Lvmin Zhang , Shengqu Cai , Muyang Li , Gordon Wetzstein , Maneesh Agrawala

Recent advancements in diffusion-based video generation have produced impressive and high-fidelity short videos. To extend these successes to generate coherent long videos, most video diffusion models (VDMs) generate videos in an…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Tianle Cheng , Zeyan Zhang , Kaifeng Gao , Jun Xiao

The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Jiamin Wang , Yichen Yao , Xiang Feng , Hang Wu , Yaming Wang , Qingqiu Huang , Yuexin Ma , Xinge Zhu

Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Huu-Loc Tran , Tinh-Anh Nguyen-Nhu , Huu-Phong Phan-Nguyen , Tien-Huy Nguyen , Nhat-Minh Nguyen-Dich , Anh Dao , Huy-Duc Do , Quan Nguyen , Hoang M. Le , Quang-Vinh Dinh

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

Motivated by augmented and virtual reality applications such as telepresence, there has been a recent focus in real-time performance capture of humans under motion. However, given the real-time constraint, these systems often suffer from…