中文
相关论文

相关论文: HiAR: Efficient Autoregressive Long Video Generati…

200 篇论文

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…

多媒体 · 计算机科学 2026-03-16 Yaofeng Su , Yuming Li , Zeyue Xue , Jie Huang , Siming Fu , Haoran Li , Ying Li , Zezhong Qian , Haoyang Huang , Nan Duan

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

计算机视觉与模式识别 · 计算机科学 2025-11-06 Mingyu Sung , Il-Min Kim , Sangseok Yun , Jae-Mo Kang

Text-guided video-to-video stylization transforms the visual appearance of a source video to a different appearance guided on textual prompts. Existing text-guided image diffusion models can be extended for stylized video synthesis.…

计算机视觉与模式识别 · 计算机科学 2023-11-27 Minshan Xie , Hanyuan Liu , Chengze Li , Tien-Tsin Wong

Spatial Transcriptomics (ST) offers spatially resolved gene expression but remains costly. Predicting expression directly from widely available Hematoxylin and Eosin (H&E) stained images presents a cost-effective alternative. However, most…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Jiarui Ouyang , Yihui Wang , Yihang Gao , Yingxue Xu , Shu Yang , Hao Chen

In recent years, data-driven techniques have greatly advanced autonomous driving systems, but the need for rare and diverse training data remains a challenge, requiring significant investment in equipment and labor. World models, which…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Haiguang Wang , Daqi Liu , Hongwei Xie , Haisong Liu , Enhui Ma , Kaicheng Yu , Limin Wang , Bing Wang

Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This limitation is associated with synchronous denoising, where…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Zijing Hu , Yunze Tong , Fengda Zhang , Junkun Yuan , Jun Xiao , Kun Kuang

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…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Yusuf Dalva , Pinar Yanardag

Recently, autoregressive (AR) video diffusion models have achieved remarkable performance. However, due to their limited training durations, a train-test gap emerges when testing at longer horizons, leading to rapid visual degradations.…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Haodong Li , Shaoteng Liu , Zhe Lin , Manmohan Chandraker

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…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Boxun Xu , Yuming Du , Zichang Liu , Siyu Yang , Ziyang Jiang , Siqi Yan , Rajasi Saha , Albert Pumarola , Wenchen Wang , Peng Li

Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all the inconveniences…

机器学习 · 计算机科学 2023-02-28 Bowen Jing , Gabriele Corso , Renato Berlinghieri , Tommi Jaakkola

Recent advances in large language models have shown that autoregressive modeling can generate complex and novel sequences that have many real-world applications. However, these models must generate outputs autoregressively, which becomes…

机器学习 · 计算机科学 2023-06-05 Asier Mujika

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Shikang Zheng , Jingkai Huang , Jiacheng Liu , Guantao Chen , Lixuan , Yuqi Lin , Peiliang Cai , Linfeng Zhang

Recent advances in diffusion models have greatly improved text-driven video generation. However, training models for long video generation demands significant computational power and extensive data, leading most video diffusion models to be…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Yunlong Yuan , Yuanfan Guo , Chunwei Wang , Hang Xu , Li Zhang

Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…

计算机视觉与模式识别 · 计算机科学 2021-06-09 Naoya Fushishita , Antonio Tejero-de-Pablos , Yusuke Mukuta , Tatsuya Harada

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Junke Wang , Zhi Tian , Xun Wang , Xinyu Zhang , Weilin Huang , Zuxuan Wu , Yu-Gang Jiang

Recent advances align diffusion models with human preferences to increase aesthetic appeal and mitigate artifacts and biases. Such methods aim to maximize a conditional output distribution aligned with higher rewards whilst not drifting far…

机器学习 · 计算机科学 2026-02-23 Ratnavibusena Don Shahain Manujith , Teoh Tze Tzun , Kenji Kawaguchi , Yang Zhang

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…

计算机视觉与模式识别 · 计算机科学 2022-06-10 Tim Brooks , Janne Hellsten , Miika Aittala , Ting-Chun Wang , Timo Aila , Jaakko Lehtinen , Ming-Yu Liu , Alexei A. Efros , Tero Karras

Video sequences often contain structured noise and background artifacts that obscure dynamic content, posing challenges for accurate analysis and restoration. Robust principal component methods address this by decomposing data into low-rank…

计算机视觉与模式识别 · 计算机科学 2026-04-27 Tristan S. W. Stevens , Oisín Nolan , Jean-Luc Robert , Ruud J. G. van Sloun

In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the observation that images exhibit local structures, and…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Yefei He , Feng Chen , Yuanyu He , Shaoxuan He , Hong Zhou , Kaipeng Zhang , Bohan Zhuang

Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. However, existing approaches typically implement iterative refinement at the application or prompting…

计算与语言 · 计算机科学 2024-10-15 Yuxi Xie , Anirudh Goyal , Xiaobao Wu , Xunjian Yin , Xiao Xu , Min-Yen Kan , Liangming Pan , William Yang Wang