English
Related papers

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

200 papers

Most existing methods for concept unlearning in text-to-image diffusion models minimize a mean squared error (MSE) loss between the denoiser outputs conditioned on a target and an anchor concept, which is implicitly the KL divergence…

Machine Learning · Computer Science 2026-05-27 Nicola Novello , Federico Fontana , Luigi Cinque , Deniz Gunduz , Andrea M. Tonello

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-02 Xin Tan , Yuetao Chen , Yimin Jiang , Xing Chen , Kun Yan , Nan Duan , Yibo Zhu , Daxin Jiang , Hong Xu

Large Vision-Language Models (LVLMs) are widely adopted for their strong multimodal capabilities, yet they raise serious concerns such as privacy leakage and harmful content generation. Machine unlearning has emerged as a promising solution…

Machine Learning · Computer Science 2026-01-30 Yejin Kim , Dongjun Hwang , Sungmin Cha , Junsuk Choe

Layout-to-Image generation aims to create complex scenes with precise control over the placement and arrangement of subjects. Existing works have demonstrated that pre-trained Text-to-Image diffusion models can achieve this goal without…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Bonan Li , Yinhan Hu , Songhua Liu , Xinchao Wang

Large Vision-Language Models (LVLMs) face a tug-of-war between powerful linguistic priors and visual evidence, often leading to \emph{semantic drift}: a progressive detachment from the input image that can abruptly emerge at specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Jiahe Chen , Jiaying He , Qiyuan Chen , Qian Shao , Jiahe Ying , Hongxia Xu , Jintai Chen , Jianwei Zheng , Jian Wu

The current large language models are mainly based on decode-only structure transformers, which have great in-context learning (ICL) capabilities. It is generally believed that the important foundation of its ICL capability is the induction…

Computation and Language · Computer Science 2024-12-06 Mingyu Xu , Wei Cheng , Bingning Wang , Weipeng Chen

While autoregressive (AR) Vision-Language-Action (VLA) models have demonstrated formidable reasoning capabilities in robotic tasks, their sequential decoding process often incurs high inference latency and may amplify error accumulation…

Robotics · Computer Science 2026-05-14 Ruiheng Wang , Shuanghao Bai , Haoran Zhang , Badong Chen , Xiangyu Xu

Video relighting offers immense creative potential and commercial value but is hindered by challenges, including the absence of an adequate evaluation metric, severe light flickering, and the degradation of fine-grained details during…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Xiangrui Liu , Haoxiang Li , Yezhou Yang

Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Elisabeth Jüttner , Janelle Pfeifer , Leona Krath , Stefan Korfhage , Hannah Dröge , Matthias B. Hullin , Markus Plack

Chinese landscape painting is a gem of Chinese cultural and artistic heritage that showcases the splendor of nature through the deep observations and imaginations of its painters. Limited by traditional techniques, these artworks were…

Multimedia · Computer Science 2024-04-22 Dingming Liu , Shaowei Li , Ruoyan Zhou , Lili Liang , Yongguan Hong , Fei Chao , Rongrong Ji

We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable typography and place an occluding object over the intended text region. This setting…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jingqi Hou , Hongtian Wang

Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Meng Shen , Minghao Wu , Deepu Rajan

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Tiezheng Zhang , Yitong Li , Yu-cheng Chou , Jieneng Chen , Alan Yuille , Chen Wei , Junfei Xiao

In recent years, large-scale pre-trained diffusion transformer models have made significant progress in video generation. While current DiT models can produce high-definition, high-frame-rate, and highly diverse videos, there is a lack of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Changgu Chen , Xiaoyan Yang , Junwei Shu , Changbo Wang , Yang Li

Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color, and ambient lighting, while preserving physical consistency…

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Long-context inference in decoder-only language models is costly because long prompts are processed during Prefill, cached at every layer, and repeatedly attended to during autoregressive Decode. We introduce \emph{Shallow Prefill, dEEp…

Artificial Intelligence · Computer Science 2026-05-08 Jungsuk Oh , Hyeseo Jeon , Hyunjune Ji , Kyongmin Kong , Jay-Yoon Lee

We hypothesize that a key bottleneck in generalizable robot manipulation is not solely data scale or policy capacity, but a structural mismatch between current visual backbones and the physical requirements of closed-loop control. While…

Robotics · Computer Science 2026-02-13 Yu Deng , Yufeng Jin , Xiaogang Jia , Jiahong Xue , Gerhard Neumann , Georgia Chalvatzaki

Recent studies have explored combining different LoRAs to jointly generate learned style and content. However, existing methods either fail to effectively preserve both the original subject and style simultaneously or require additional…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Ziheng Ouyang , Zhen Li , Qibin Hou

We study training-free image editing on Qwen-Image-Edit-2511, a 60-block multi-modal diffusion transformer (MMDiT) that concatenates noise and source-image tokens within a single attention stream. We make three contributions. (i) We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Guandong Li , Mengxia Ye