English
Related papers

Related papers: Error Analyses of Auto-Regressive Video Diffusion …

200 papers

Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Houyuan Chen , Hong Li , Xianghao Kong , Tianrui Zhu , Shaocong Xu , Weiqing Xiao , Yuwei Guo , Chongjie Ye , Lvmin Zhang , Hao Zhao , Anyi Rao

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

Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Haoyu Chen , Qing Liu , Yuqian Zhou , He Zhang , Zhaowen Wang , Mengwei Ren , Jingjing Ren , Xiang Wang , Zhe Lin , Lei Zhu

Building on the momentum of image generation diffusion models, there is an increasing interest in video-based diffusion models. However, video generation poses greater challenges due to its higher-dimensional nature, the scarcity of…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Aimon Rahman , Malsha V. Perera , Vishal M. Patel

We tackle the dual challenges of video understanding and controllable video generation within a unified diffusion framework. Our key insights are two-fold: geometry-only cues (e.g., depth, edges) are insufficient: they specify layout but…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Dianbing Xi , Jiepeng Wang , Yuanzhi Liang , Xi Qiu , Jialun Liu , Hao Pan , Yuchi Huo , Rui Wang , Haibin Huang , Chi Zhang , Xuelong Li

We present a controlled empirical comparison between autoregressive (AR) and masked diffusion (MDLM) language models. Both models are trained on identical data (50M tokens from TinyStories), identical compute budget (20,000 steps, batch…

Computation and Language · Computer Science 2026-03-24 Caio Vicentino

Real-world perception and interaction are inherently multimodal, encompassing not only language but also vision and speech, which motivates the development of "Omni" MLLMs that support both multimodal inputs and multimodal outputs. While a…

Machine Learning · Computer Science 2026-01-27 Dongjie Cheng , Ruifeng Yuan , Yongqi Li , Runyang You , Wenjie Wang , Liqiang Nie , Lei Zhang , Wenjie Li

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image…

Cryptography and Security · Computer Science 2024-01-01 Sheng-Yen Chou , Pin-Yu Chen , Tsung-Yi Ho

Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs…

Computation and Language · Computer Science 2024-04-03 Xingwei Tan , Yuxiang Zhou , Gabriele Pergola , Yulan He

Bitstream-corrupted video recovery aims to restore realistic content degraded during video storage or transmission. Existing methods typically assume that predefined masks of corrupted regions are available, but manually annotating these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Shuyun Wang , Hu Zhang , Xin Shen , Dadong Wang , Xin Yu

Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR models while maintaining overall generation quality remains an…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Haipeng Fan , Shiyuan Zhang , Baohunesitu , Zihang Guo , Huaiwen Zhang

Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Dohun Lee , Chun-Hao Paul Huang , Xuelin Chen , Jong Chul Ye , Duygu Ceylan , Hyeonho Jeong

Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Boming Tan , Xiangdong Zhang , Ning Liao , Yuqing Zhang , Shaofeng Zhang , Xue Yang , Qi Fan , Yanyong Zhang

Multimodal Large Language Models (MLLMs) perform well in video understanding but degrade on long videos due to fixed-length context and weak long-term dependency modeling. Retrieval-Augmented Generation (RAG) can expand knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Zhucun Xue , Jiangning Zhang , Xurong Xie , Yuxuan Cai , Yong Liu , Xiangtai Li , Dacheng Tao

We present a unified network for simultaneously generating videos and their corresponding entity segmentation and depth maps from text prompts. We utilize colormap to represent entity masks and depth maps, tightly integrating dense…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Lehan Yang , Lu Qi , Xiangtai Li , Sheng Li , Varun Jampani , Ming-Hsuan Yang

Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Desai Xie , Zhan Xu , Yicong Hong , Hao Tan , Difan Liu , Feng Liu , Arie Kaufman , Yang Zhou

Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are…

Image and Video Processing · Electrical Eng. & Systems 2022-12-13 Dario Fuoli , Zhiwu Huang , Danda Pani Paudel , Luc Van Gool , Radu Timofte

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Junbo Wang , Liangyu Fu , Yuke Li , Yining Zhu , Ya Jing , Xuecheng Wu , Jiangbin Zheng

The recovery of training data from generative models ("model inversion") has been extensively studied for diffusion models in the data domain as a memorization/overfitting phenomenon. Latent diffusion models (LDMs), which operate on the…

Machine Learning · Computer Science 2026-03-26 Mingxing Rao , Bowen Qu , Daniel Moyer

While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To…

Computation and Language · Computer Science 2026-04-14 Zhengnan Guo , Fei Tan