English
Related papers

Related papers: Anchor Forcing: Anchor Memory and Tri-Region RoPE …

200 papers

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Boxun Xu , Yuming Du , Zichang Liu , Siyu Yang , Ziyang Jiang , Siqi Yan , Rajasi Saha , Albert Pumarola , Wenchen Wang , Peng Li

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Chong Cheng , Xianda Chen , Tao Xie , Wei Yin , Weiqiang Ren , Qian Zhang , Xiaoyang Guo , Hao Wang

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

Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity problem: pretrained video diffusion transformers already…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Tianshuo Xu , Yichen Xie , Depu Meng , Chensheng Peng , Quentin Herau , Bo Jiang , Yihan Hu , Wei Zhan

Real-time talking avatar generation requires low latency and minute-level temporal stability. Autoregressive (AR) forcing enables streaming inference but suffers from exposure bias, which causes errors to accumulate and become irreversible…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Liyuan Cui , Wentao Hu , Wenyuan Zhang , Zesong Yang , Fan Shi , Xiaoqiang Liu

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Shuo Chen , Cong Wei , Sun Sun , Ping Nie , Kai Zhou , Ge Zhang , Ming-Hsuan Yang , Wenhu Chen

Video generation with controllable camera viewpoints is essential for applications such as interactive content creation, gaming, and simulation. Existing methods typically adapt pre-trained video models using camera poses relative to a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Chunyang Li , Yuanbo Yang , Jiahao Shao , Hongyu Zhou , Katja Schwarz , Yiyi Liao

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Sihui Ji , Xi Chen , Shuai Yang , Xin Tao , Pengfei Wan , Hengshuang Zhao

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Hang Guo , Zhaoyang Jia , Jiahao Li , Bin Li , Yuanhao Cai , Jiangshan Wang , Yawei Li , Yan Lu

Digital characters are central to modern media, yet generating character videos with long-duration, consistent multi-view appearance and expressive identity remains challenging. Existing approaches either provide insufficient context to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Yuhang Yang , Fan Zhang , Huaijin Pi , Shuai Guo , Guowei Xu , Wei Zhai , Yang Cao , Zheng-Jun Zha

Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Min Zhao , Hongzhou Zhu , Kaiwen Zheng , Zihan Zhou , Bokai Yan , Xinyuan Li , Xiao Yang , Chongxuan Li , Jun Zhu

Video generation has seen remarkable progress thanks to advancements in generative deep learning. However, generating long sequences remains a significant challenge. Generated videos should not only display coherent and continuous movement…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Jingbo Yang , Adrian G. Bors

Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework…

Multimedia · Computer Science 2026-03-16 Yaofeng Su , Yuming Li , Zeyue Xue , Jie Huang , Siming Fu , Haoran Li , Ying Li , Zezhong Qian , Haoyang Huang , Nan Duan

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Yawen Luo , Xiaoyu Shi , Junhao Zhuang , Yutian Chen , Quande Liu , Xintao Wang , Pengfei Wan , Tianfan Xue

Multimodal large language models (MLLMs) have made significant progress in visual-language reasoning, but their ability to efficiently handle long videos remains limited. Despite recent advances in long-context MLLMs, storing and attending…

Computer Vision and Pattern Recognition · Computer Science 2025-08-22 Yanlai Yang , Zhuokai Zhao , Satya Narayan Shukla , Aashu Singh , Shlok Kumar Mishra , Lizhu Zhang , Mengye Ren

Generating long videos that can show complex stories, like movie scenes from scripts, has great promise and offers much more than short clips. However, current methods that use autoregression with diffusion models often struggle because…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Guangcong Zheng , Jianlong Yuan , Bo Wang , Haoyang Huang , Guoqing Ma , Nan Duan

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Chao Yuan , Pan Li

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Xiaofei Wu , Guozhen Zhang , Zhiyong Xu , Yuan Zhou , Qinglin Lu , Xuming He

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Yunhong Lu , Yanhong Zeng , Haobo Li , Hao Ouyang , Qiuyu Wang , Ka Leong Cheng , Jiapeng Zhu , Hengyuan Cao , Zhipeng Zhang , Xing Zhu , Yujun Shen , Min Zhang