English
Related papers

Related papers: OmniForcing: Unleashing Real-time Joint Audio-Visu…

200 papers

This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a…

Machine Learning · Computer Science 2024-12-11 Boyuan Chen , Diego Marti Monso , Yilun Du , Max Simchowitz , Russ Tedrake , Vincent Sitzmann

We introduce OneDiffusion, a versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. It enables conditional generation from inputs such as text, depth, pose,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Duong H. Le , Tuan Pham , Sangho Lee , Christopher Clark , Aniruddha Kembhavi , Stephan Mandt , Ranjay Krishna , Jiasen Lu

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Bin Wu , Mengqi Huang , Shaojin Wu , Weinan Jia , Yuxin Wang , Zhendong Mao , Yongdong Zhang

Diffusion models have demonstrated remarkable performance in generating unimodal data across various tasks, including image, video, and text generation. On the contrary, the joint generation of multimodal data through diffusion models is…

Machine Learning · Computer Science 2025-06-16 Kevin Rojas , Yuchen Zhu , Sichen Zhu , Felix X. -F. Ye , Molei Tao

Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Joonghyuk Shin , Zhengqi Li , Richard Zhang , Jun-Yan Zhu , Jaesik Park , Eli Shechtman , Xun Huang

Real-time text-driven joint audio-video avatar generation requires jointly synthesizing portrait video and speech with high fidelity and precise synchronization, yet existing audio-visual diffusion models remain too slow for interactive use…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Chunyu Li , Jiaye Li , Ruiqiao Mei , Haoyuan Xia , Hao Zhu , Jingdong Wang , Siyu Zhu

Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, existing controllable generation frameworks are typically…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Liyang Li , Wen Wang , Canyu Zhao , Tianjian Feng , Zhiyue Zhao , Hao Chen , Chunhua Shen

Deploying massive diffusion models for real-time, infinite-duration, audio-driven avatar generation presents a significant engineering challenge, primarily due to the conflict between computational load and strict latency constraints.…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Le Shen , Qian Qiao , Tan Yu , Ke Zhou , Tianhang Yu , Yu Zhan , Zhenjie Wang , Ming Tao , Shunshun Yin , Siyuan Liu

Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Chuyang Zhao , Yuxing Song , Wenhao Wang , Haocheng Feng , Errui Ding , Yifan Sun , Xinyan Xiao , Jingdong Wang

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Zhening Xing , Gereon Fox , Yanhong Zeng , Xingang Pan , Mohamed Elgharib , Christian Theobalt , Kai Chen

Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synchronization. Reinforcement Learning (RL) offers a promising…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Guohui Zhang , XiaoXiao Ma , Jie Huang , Hang Xu , Hu Yu , Siming Fu , Yuming Li , Zeyue Xue , Lin Song , Haoyang Huang , Nan Duan , Feng Zhao

High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical inference infeasible. To address this, we introduce HiStream, an…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Haonan Qiu , Shikun Liu , Zijian Zhou , Zhaochong An , Weiming Ren , Zhiheng Liu , Jonas Schult , Sen He , Shoufa Chen , Yuren Cong , Tao Xiang , Ziwei Liu , Juan-Manuel Perez-Rua

Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Zhenglin Cheng , Peng Sun , Jianguo Li , Tao Lin

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Junpeng Jiang , Gangyi Hong , Miao Zhang , Hengtong Hu , Kun Zhan , Rui Shao , Liqiang Nie

We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency. Unlike existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Yiyi Cai , Yuhan Wu , Kunhang Li , You Zhou , Bo Zheng , Haiyang Liu

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Yongqi Yang , Huayang Huang , Xu Peng , Xiaobin Hu , Donghao Luo , Jiangning Zhang , Chengjie Wang , Yu Wu

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

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

Although significant progress has been made in audio-driven talking head generation, text-driven methods remain underexplored. In this work, we present OmniTalker, a unified framework that jointly generates synchronized talking audio-video…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Zhongjian Wang , Peng Zhang , Jinwei Qi , Guangyuan Wang , Chaonan Ji , Sheng Xu , Bang Zhang , Liefeng Bo