English
Related papers

Related papers: SaRA: High-Efficient Diffusion Model Fine-tuning w…

200 papers

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Zongsheng Yue , Kang Liao , Chen Change Loy

While perspective is a well-studied topic in art, it is generally taken for granted in images. However, for the recent wave of high-quality image synthesis methods such as latent diffusion models, perspective accuracy is not an explicit…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Rishi Upadhyay , Howard Zhang , Yunhao Ba , Ethan Yang , Blake Gella , Sicheng Jiang , Alex Wong , Achuta Kadambi

Diffusion models have achieved remarkable success in image generation, with applications broadening across various domains. Inpainting is one such application that can benefit significantly from diffusion models. Existing methods either…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Sora Kim , Sungho Suh , Minsik Lee

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and lower memory usage, they do not decrease computational cost.…

An increasing number of autoregressive models, such as MAR, FlowAR, xAR, and Harmon adopt diffusion sampling to improve the quality of image generation. However, this strategy leads to low inference efficiency, because it usually takes 50…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Qinyu Zhao , Jaskirat Singh , Ming Xu , Akshay Asthana , Stephen Gould , Liang Zheng

Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent generation, arguably due to the inherent locality of their denoising mechanisms. This can yield…

Machine Learning · Computer Science 2026-02-04 Wenshuai Zhao , Zhiyuan Li , Yi Zhao , Mohammad Hassan Vali , Martin Trapp , Joni Pajarinen , Juho Kannala , Arno Solin

Model merging is to combine fine-tuned models derived from multiple domains, with the intent of enhancing the model's proficiency across various domains. The principal concern is the resolution of parameter conflicts. A substantial amount…

Computation and Language · Computer Science 2024-03-06 Yaochen Zhu , Rui Xia , Jiajun Zhang

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Wei Dong , Xing Zhang , Bihui Chen , Dawei Yan , Zhijun Lin , Qingsen Yan , Peng Wang , Yang Yang

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite…

Machine Learning · Computer Science 2026-04-24 Bingcong Li , Yilang Zhang , Georgios B. Giannakis

Efficiently adapting large foundation models is critical, especially with tight compute and memory budgets. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA offer limited granularity and effectiveness in few-parameter regimes. We…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ahmet Bilican , M. Akın Yılmaz , A. Murat Tekalp , R. Gökberk Cinbiş

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Yufei Wang , Yi Yu , Wenhan Yang , Lanqing Guo , Lap-Pui Chau , Alex C. Kot , Bihan Wen

Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Mengmeng Wang , Dengyang Jiang , Liuzhuozheng Li , Yucheng Lin , Guojiang Shen , Xiangjie Kong , Yong Liu , Guang Dai , Jingdong Wang

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Machine Learning · Computer Science 2024-11-05 Shengchao Hu , Wanru Zhao , Weixiong Lin , Li Shen , Ya Zhang , Dacheng Tao

Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Tianshu Kuai , Sina Honari , Igor Gilitschenski , Alex Levinshtein

Sparse fine-tuning techniques adapt LLMs to downstream tasks by only tuning a sparse subset of model parameters. However, the effectiveness of sparse adaptation depends on optimally selecting the model parameters to be fine-tuned. In this…

Machine Learning · Computer Science 2025-10-23 Anand Choudhary , Yasser Sulaıman , Lukas Mauch , Ghouthi Boukli Hacene , Fabien Cardinaux , Antoine Bosselut

This work presents TV-LoRA, a novel method for low-dose sparse-view CT reconstruction that combines a diffusion generative prior (NCSN++ with SDE modeling) and multi-regularization constraints, including anisotropic TV and nuclear norm…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Zongyin Deng , Qing Zhou , Yuhao Fang , Zijian Wang , Yao Lu , Ye Zhang , Chun Li

Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstream tasks, without requiring additional fine-tuning.…

We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method achieves sampling by "pulling back" the dynamics of the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Yash Savani , Marc Finzi , J. Zico Kolter

Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of…

Computation and Language · Computer Science 2024-02-05 Alan Ansell , Ivan Vulić , Hannah Sterz , Anna Korhonen , Edoardo M. Ponti