English
Related papers

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

200 papers

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mingqiang Wu , Weilun Feng , Zhefeng Zhang , Haotong Qin , Yuqi Li , Guoxin Fan , Xiaokun Liu , Zhulin An , Libo Huang , Yongjun Xu , Chuanguang Yang

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…

Computation and Language · Computer Science 2025-10-10 Zhanqiu Hu , Jian Meng , Yash Akhauri , Mohamed S. Abdelfattah , Jae-sun Seo , Zhiru Zhang , Udit Gupta

Through systematic experiments on long-context generation, we observe a damaging failure mode in which decoding can collapse into persistent repetition loops. We find that this degeneration is driven by collapsed attention patterns, where a…

Artificial Intelligence · Computer Science 2026-04-14 Dongjie Xu , Hao Wu , Weijie Shi , Yue Cui , Yuanjun Liu , Jiawei Li , Haolun Ma , An Liu , Jia Zhu , Jiajie Xu

Video generative models achieve high-quality synthesis from natural-language prompts by leveraging large-scale web data. However, this training paradigm inherently exposes them to unsafe biases and harmful concepts, introducing the risk of…

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Shengrong Gu , Ye Wang , Song Wu , Rui Ma , Qian Wang , Lanjun Wang , Zili Yi

Latent Video Diffusion Models (LVDMs) have achieved state-of-the-art generative quality for image and video generation; however, they remain brittle under noisy conditioning, where small perturbations in text or multimodal embeddings can…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Chika Maduabuchi , Hao Chen , Yujin Han , Jindong Wang

We propose \textbf{IC-Effect}, an instruction-guided, DiT-based framework for few-shot video VFX editing that synthesizes complex effects (\eg flames, particles and cartoon characters) while strictly preserving spatial and temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Yuanhang Li , Yiren Song , Junzhe Bai , Xinran Liang , Hu Yang , Libiao Jin , Qi Mao

Video colour editing is a crucial task for content creation, yet existing solutions either require painstaking frame-by-frame manipulation or produce unrealistic results with temporal artefacts. We present a practical, training-free…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Chaitat Utintu , Pinaki Nath Chowdhury , Aneeshan Sain , Subhadeep Koley , Ayan Kumar Bhunia , Yi-Zhe Song

Although powerful for image generation, consistent and controllable video is a longstanding problem for diffusion models. Video models require extensive training and computational resources, leading to high costs and large environmental…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Muhammad Haaris Khan , Hadrien Reynaud , Bernhard Kainz

Sequence-to-sequence tasks often benefit from long contexts, but the quadratic complexity of self-attention in standard Transformers renders this non-trivial. During generation, temporary representations -stored in the so-called KV…

Computation and Language · Computer Science 2025-03-14 Vivek Chari , Guanghui Qin , Benjamin Van Durme

Existing Large Vision-Language Models (LVLMs) exhibit insufficient visual attention, leading to hallucinations. To alleviate this problem, some previous studies adjust and amplify visual attention. These methods present a limitation that…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Jingyi Wang , Fei Li , Rujie Liu

Diffusion models have demonstrated remarkable success in image generation and editing, with recent advancements enabling albedo-preserving image relighting. However, applying these models to video relighting remains challenging due to the…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Ye Fang , Zeyi Sun , Shangzhan Zhang , Tong Wu , Yinghao Xu , Pan Zhang , Jiaqi Wang , Gordon Wetzstein , Dahua Lin

Diffusion Transformer has shown remarkable abilities in generating high-fidelity videos, delivering visually coherent frames and rich details over extended durations. However, existing video generation models still fall short in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Zhaoyang Li , Dongjun Qian , Kai Su , Qishuai Diao , Xiangyang Xia , Chang Liu , Wenfei Yang , Tianzhu Zhang , Zehuan Yuan

Diffusion models have demonstrated impressive performance in text-to-image generation. They utilize a text encoder and cross-attention blocks to infuse textual information into images at a pixel level. However, their capability to generate…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Luping Liu , Zijian Zhang , Yi Ren , Rongjie Huang , Xiang Yin , Zhou Zhao

Sign language translation (SLT) is challenging, as it involves converting sign language videos into natural language. Previous studies have prioritized accuracy over diversity. However, diversity is crucial for handling lexical and…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 JiHwan Moon , Jihoon Park , Jungeun Kim , Jongseong Bae , Hyeongwoo Jeon , Ha Young Kim

Diffusion models excel at photorealistic synthesis but struggle with precise object counts, especially in high-density settings. We introduce COUNTLOOP, a training-free framework that achieves precise instance control through iterative,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Anindya Mondal , Ayan Banerjee , Sauradip Nag , Josep Llados , Xiatian Zhu , Anjan Dutta

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yingqing He , Shaoshu Yang , Haoxin Chen , Xiaodong Cun , Menghan Xia , Yong Zhang , Xintao Wang , Ran He , Qifeng Chen , Ying Shan

We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Moayed Haji-Ali , Willi Menapace , Aliaksandr Siarohin , Ivan Skorokhodov , Alper Canberk , Kwot Sin Lee , Vicente Ordonez , Sergey Tulyakov

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Ivan Skorokhodov , Sharath Girish , Benran Hu , Willi Menapace , Yanyu Li , Rameen Abdal , Sergey Tulyakov , Aliaksandr Siarohin