Diffusion Model Fine-Tuning

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, against 2 the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 116

All topics

Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
Oct 7, 2026Hanqiu Li Cai, Chema GarabitoT2I Diffusion Models Pixel-Space Diffusion Models
SperidLabs
Are Parameter-Efficient Fine-tuning Methods Really Different?
Oct 6, 2026Yikuan Li, Pinyan Lu, Fanghui LiuParameter-Efficient Fine-Tuning Low-Rank Adaptation
Department of Statistics, The University of Warwick, UK. · Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, China. · School of Mathematical Sciences, Institute of Natural Sciences and MOE-LSC, Shanghai Jiao Tong University, China.
MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
Oct 6, 2026Syed Ibrahim Omer, Ginny Y. Wong, Xiangyu ZhaoState Space Models Diffusion Model Fine-Tuning
Department of Data Science City University of Hong Kong · NVIDIA AI Technology Center NVIDIA, Santa Clara, USA
LiDAR Resolution Recovery via Foundation-Model-Guided Diffusion
Oct 6, 2026Samed Doğan, Nico Leuze, Alfred SchöttlDiffusion Model Guidance Depth Completion
Dept. of Electrical Engineering and Information Technology Munich University of Applied Sciences, 80335 Munich, Germany
Adapting a Latent Audio Diffusion Model to Historical Guqin Recordings: A Listening-Driven Case Study
Oct 5, 2026Huanchen CaiText-to-Music Generation Music Generation Evaluation
Division of Speech, Music and Hearing (TMH) KTH Royal Institute of Technology, Stockholm, Sweden
CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork
Oct 1, 2026Wojciech Gromski, Patryk Krukowski, Jan Miksa +2Subject-Driven Image Generation T2I Generation
Wrocław University of Science and Technology · IDEAS Research Institute · Jagiellonian University, Krak´ow +2
Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models
Sep 30, 2026Maksim Bobrin, Maksim Zhdanov, Dmitry DylovDiffusion Model Alignment Constrained Generative Modeling
AXXX · Applied AI Institute · MBZUAI
CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models
Sep 30, 2026Shu Yu, Chaochao LuDiffusion Model Fine-Tuning Compositional T2I Generation
Shanghai Artificial Intelligence Laboratory, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Fudan University, Shanghai, China
ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images
Sep 30, 2026Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah +1Diffusion Model Guidance Classifier-Free Guidance
University of Illinois Urbana-Champaign
Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting
Sep 29, 2026Loay Mualem, Lluís Pastor-Pérez, Vinh Tong +4Masked Diffusion Models Diffusion Model Fine-Tuning
IMPRS-IS · Institute for AI, University of Stuttgart · Bitdefender
ExploreNet: Learning Where to Explore in Diffusion GRPO
Sep 29, 2026Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov +1Diffusion Model Fine-Tuning RL Exploration
University of Washington
Adversarial Training for Pixel Diffusion
Sep 29, 2026Xin Lin, Zhifei Zhang, Yuqian Zhou +4Adversarial Training Pixel-Space Diffusion Models
UC San Diego · Adobe Research · Work done during an internship at Adobe Research +1
On Trajectory-Aware Training for Masked Diffusion Language Models
Sep 29, 2026Manuel Madeira, Amitis Shidani, Alice Bizeul +6Masked Diffusion Models Diffusion Language Model Inference
EPFL · Apple · Georgia Institute of Technology
MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators
Sep 29, 2026Haocheng Tang, Tianchi Xie, Xingqiao LinFlow Matching MeanFlow
Northeastern University Boston, MA 02115, USA · Tsinghua University Beijing, 100084, PRC · Carnegie Mellon University Pittsburgh, PA 15213, USA
Triangular Resampling for Long-Horizon Motion Generation
Sep 28, 2026Kunhang Li, Yiyi Cai, Xiangyue Zhang +5Motion Diffusion Models Human Motion Generation
The University of Tokyo · Alaya Lab · Japan Advanced Institute of Science and Technology
Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation
Sep 27, 2026Xuan Qi, Yi Wei, Daniele Berardini +2Unsupervised Domain Adaptation Domain Adaptation
AI for Good (AIGO), Istituto Italiano di Tecnologia, Genoa, Italy · DITEN, University of Genoa, Genoa, Italy · National Key Laboratory of Novel Software Technology, Nanjing University, China +3
Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning
Sep 27, 2026Toyota Li, David Zhao, Alan ZhaoReinforcement Learning Constrained RL
Tencent
DOHF: Online Diffusion Fine-tuning with Doob's $h$ -transform Guidance
Sep 25, 2026Zhengyi Guo, Jiayuan Sheng, Wenpin Tang +1Diffusion Model Alignment Diffusion Model Guidance
Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement
Sep 21, 2026Qing Yao, Lijian Gao, Qirong MaoDiffusion Model Fine-Tuning Speech Enhancement
School of Computer Science and Communication Engineering, Jiangsu University Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang, China
Principal-timestep Restricted Init via Sparse Matrix-decomposition in Flow-matching
Sep 14, 2026Jiayang Gu, Zheng Fang, Lichaun Xiang +3Flow Matching Diffusion Model Fine-Tuning
University of Warwick · Bytedance
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution
Sep 14, 2026Shuhao Han, Wenjie Liao, Hayden Vance +4Diffusion Models for Image Restoration Diffusion Model Fine-Tuning
VCIP, CS, Nankai University · Independent Researcher
GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models
Sep 14, 2026Qinghui Gong, Yihuai Liang, Yuanlun Xie +3Diffusion Model Fine-Tuning Diffusion Model Unlearning
School of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, China · School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu, China · Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China +1
Understanding LoRA Rank Trade-offs in Diffusion Model Fine-Tuning
Sep 12, 2026Iman Khazrak, Narges Nejad, Mostafa M. Rezaee +1Diffusion Model Fine-Tuning Low-Rank Adaptation
Department of Computer Science, Bowling Green State University, Bowling Green, OH, USA. · Department of Management and Marketing, Angelo State University, San Angelo, TX, USA.
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Sep 8, 2026Igor Pavlovic, Thiemo Wandel, Anton Obukhov +6Diffusion Transformer OOD Generalization
EPFL, HUAWEI Bayer Lab, Switzerland · HUAWEI Bayer Lab, Switzerland · University of Bologna, Italy +1
Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure
Sep 1, 2026Qinghui Gong, Xunlei Chen, Yu-Xuan Zhang +2Diffusion Model Fine-Tuning Low-Rank Adaptation
Southwest Jiaotong University · University of Electronic Science and Technology of China
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss
Aug 11, 2026Mingju Gao, Jingkai Zhou, Kun Gai +2Diffusion Model Alignment Diffusion Model Fine-Tuning
Peking University · KlingAI Research
High-Quality Exposure Correction with Diffusion-Based Image Generation Priors
Aug 9, 2026Ziwen Li, Meng Cao, Jinpu Zhang +4Image Enhancement Diffusion Model Fine-Tuning
National Key Laboratory of Science and Technology on Multispectral Information Processing, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · National University of Defense Technology, Changsha, China +1
PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model
Aug 7, 2026Renye Yan, Jikang Cheng, You Wu +4Intrinsic Reward Methods Reinforcement Learning
Peking University Beijing, China
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
Aug 6, 2026Rui Li, Yuanzhi Liang, Ke Hao +4Diffusion Model Alignment Video Diffusion Models
University of Science and Technology of China, Hefei, China · Institute of Artificial Intelligence, China Telecom (TeleAI), Shanghai, China · Shanghai Jiao Tong University, Shanghai, China
When does training on downscaled images yield the same gradients?
Aug 5, 2026Seunghyun JiDiffusion Transformer Diffusion Model Fine-Tuning
Independent researcher

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning

Hanqiu Li Cai, Chema Garabito

SperidLabs

T2I Diffusion Models Pixel-Space Diffusion Models Diffusion Transformer Diffusion Model Fine-Tuning Diffusion Models for Image Restoration

Open paper AskPDF arXiv

Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We test this claim along both routes to a pixel-space backbone. We pretrain Iris-3B, a 3B-parameter pixel-space text-to-image transformer, from scratch through a

256\to512\to1024

curriculum, after first ablating the prediction target and representation alignment at

256^2

to decide what to scale. We also convert a pretrained latent model, FLUX.2 Klein base 4B, to pixel space. We fine-tune both families for monocular depth estimation and for image restoration/super-resolution. We find no significant improvement from using a pixel-space generative prior. Fine-tuned for depth with one matched direct-regression recipe, Iris-3B is level with the latent FLUX.2 Klein and the converted pixel FLUX.2 Klein falls behind it, and on

4\times

DIV2K restoration neither pixel model beats a latent FLUX.2 Klein fine-tune, the converted one trailing it slightly. We document the recipes, the failure modes and the remaining confounds behind this negative result. Nevertheless, Iris-3B shows that pixel-space pretraining with the pixel-transformer (PiT) head of PixelDiT scales to 3B parameters and to text-to-image quality competitive with latent models, matching Qwen-Image on OneIG under the official evaluators at

1024^2

. We release its weights and training code in the hope that they help pave the way for further work on pixel-space generation.

Momentum

Related topics

Latest papers 116