English
Related papers

Related papers: When to Lock Attention: Training-Free KV Control i…

200 papers

Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Tianrui Zhu , Shiyi Zhang , Jiawei Shao , Yansong Tang

Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Ryugo Morita , Stanislav Frolov , Brian Bernhard Moser , Takahiro Shirakawa , Ko Watanabe , Andreas Dengel , Jinjia Zhou

Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind…

Computation and Language · Computer Science 2025-07-04 Chengyue Wu , Hao Zhang , Shuchen Xue , Zhijian Liu , Shizhe Diao , Ligeng Zhu , Ping Luo , Song Han , Enze Xie

The task of Image-to-Video (I2V) generation aims to synthesize a video from a reference image and a text prompt. This requires diffusion models to reconcile high-frequency visual constraints and low-frequency textual guidance during the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Yuanyang Yin , Yufan Deng , Shenghai Yuan , Kaipeng Zhang , Xiao Yang , Feng Zhao

Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Minghao Chen , Iro Laina , Andrea Vedaldi

When editing a video, a piece of attractive background music is indispensable. However, video background music generation tasks face several challenges, for example, the lack of suitable training datasets, and the difficulties in flexibly…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Sizhe Li , Yiming Qin , Minghang Zheng , Xin Jin , Yang Liu

Recent Video Large Language Models (Video-LLMs) have demonstrated strong capability in video understanding, yet they still suffer from hallucinations. Existing mitigation methods typically rely on training, input modification, auxiliary…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Zijian Liu , Sihan Cao , Pengcheng Zheng , Kuien Liu , Caiyan Qin , Xiaolin Qin , Jiwei Wei , Chaoning Zhang

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

Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Zeyu Zhang , Shuning Chang , Yuanyu He , Yizeng Han , Jiasheng Tang , Fan Wang , Bohan Zhuang

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yicheng Ji , Zhizhou Zhong , Jun Zhang , Qin Yang , XiTai Jin , Ying Qin , Wenhan Luo , Shuiyang Mao , Wei Liu , Huan Li

Diffusion Transformers (DiTs) have recently driven significant progress in text-to-video (T2V) generation. However, generating multiple videos with consistent characters and backgrounds remains a significant challenge. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Han Yan , Xibin Song , Yifu Wang , Hongdong Li , Pan Ji , Chao Ma

Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Junpeng Jiang , Gangyi Hong , Lijun Zhou , Enhui Ma , Hengtong Hu , Xia Zhou , Jie Xiang , Fan Liu , Kaicheng Yu , Haiyang Sun , Kun Zhan , Peng Jia , Miao Zhang

Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Sangwon Jang , Taekyung Ki , Jaehyeong Jo , Jaehong Yoon , Soo Ye Kim , Zhe Lin , Sung Ju Hwang

We introduce a method for composing object-level visual prompts within a text-to-image diffusion model. Our approach addresses the task of generating semantically coherent compositions across diverse scenes and styles, similar to the…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Gaurav Parmar , Or Patashnik , Kuan-Chieh Wang , Daniil Ostashev , Srinivasa Narasimhan , Jun-Yan Zhu , Daniel Cohen-Or , Kfir Aberman

Video moment retrieval and highlight detection have received attention in the current era of video content proliferation, aiming to localize moments and estimate clip relevances based on user-specific queries. Given that the video content…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Henghao Zhao , Kevin Qinghong Lin , Rui Yan , Zechao Li

Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yu Lu , Yuanzhi Liang , Linchao Zhu , Yi Yang

Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Yang Deng , David Mould , Paul L. Rosin , Yu-Kun Lai

Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Jung Yi , Wooseok Jang , Paul Hyunbin Cho , Jisu Nam , Heeji Yoon , Seungryong Kim

Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Guandong Li

Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV cache grows with…

‹ Prev 1 2 3 10 Next ›