Diffusion Model Fine-Tuning

Ask about this topic

Overview

Diffusion model fine-tuning studies how to adapt pretrained image, video, audio, molecular, and language generators without rebuilding them from scratch. Parameter-efficient methods such as LoRA, prompt tuning, and adapters support personalization and domain adaptation, while supervised training and self-generated trajectories target tasks such as image editing, restoration, and masked-language-model refinement. For preference alignment and constrained generation, reinforcement learning methods such as GRPO, reward matching, and distillation optimize outputs using reward signals, often on benchmarks for text-image alignment, generation quality, or downstream utility. A central tension is improving the requested behavior while preserving the model’s general capabilities and diversity, with training cost, limited data, and reward hacking complicating that balance.

Latest papers

CardsList

181 papers32 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

  1. A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation

    Oct 27, 2026Wenwu Tang, Dong Wang, Yun Cheng +1Diffusion Model DistillationDiffusion Models

    Graz University of Technology · Swiss Data Science Center, Switzerland · Complexity Science Hub, Austria

  2. Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders

    Oct 23, 2026Yiran Xiahou, Siliang Qin, Kai Chen +2Diffusion Model UnlearningConcept Erasure

    Institute of Information Engineering, Chinese Academy of Sciences, China · Department of Computer Science, Metropolitan College, Boston University, USA · Institute of Data Science, NationalUniversity of SingaporeSingapore, Singapore

  3. DualHeads: Reward-tilted few-step diffusion made simple

    Oct 20, 2026Yuanzhi Zhu, Eleftherios Tsonis, Simo Alami Chehboune +3Diffusion-Based Image GenerationDiffusion Model Fine-Tuning

    LIX, École Polytechnique, CNRS, IPP · Inria at Univ. Grenoble Alpes, CNRS, LJK

  4. When Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-Tuning

    Oct 20, 2026Wang RuLatent Space GeometryDiffusion Model Fine-Tuning

    Department of Chemical Engineering, Tsinghua University

  5. LED: Improving Masked Diffusion Language Models by Lookahead Editing

    Oct 16, 2026Yuyan Zhou, Zeyuan Yang, Yuxuan Song +5Diffusion Language Model DecodingMasked Diffusion Models

    Department of Computer Science and Engineering, The Hong Kong University of Science and Technology · ByteDance Seed · Institute for AI Industry Research (AIR), Tsinghua University +1

  6. DiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation

    Oct 16, 2026Jiayuan Wang, Tongyao PangRL for Image GenerationRL for Diffusion Models

    Qiuzhen College, Tsinghua University, Beijing 100084, China · Yau Mathematical Sciences Center, Shuangqing Complex, Tsinghua University, Beijing 100084, China

  7. FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers

    Oct 15, 2026Ngan Nguyen, Dung Nguyen, Quan Dao +4Controllable Image GenerationConditional Image Generation

    Qualcomm AI Research · Rutgers University · Adelaide University +1

  8. Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost

    Oct 14, 2026Eliot Beyler, Francis BachDiffusion Model Fine-TuningFlow-Based Generative Modeling

    Inria, Ecole Normale Supérieure, PSL Research University

  9. MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs

    Oct 13, 2026Reyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang +1T2I GenerationT2I Diffusion Models

  10. Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models

    Oct 13, 2026Miao Li, Hanyang Jiang, Hengyu Fu +8Diffusion Language ModelsDiffusion Model Fine-Tuning

    Georgia Institute of Technology · University of California, Berkeley · University of Chicago +1

  11. GuidanceNFT: NFT-Based Reward Fine-Tuning of Guided Diffusion Models

    Oct 11, 2026Jiayin Liu, Zeyu Michael Li, Bingshuo Qian +1Diffusion Model Fine-TuningT2I Diffusion Models

    Tsinghua University · Duke University

  12. DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

    Oct 8, 2026Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang +6Diffusion Model Fine-TuningRL for Diffusion Models

    HPC-AI Lab, National University of Singapore · Kling AI · HKUST

  13. Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning

    Oct 8, 2026Julian Kleutgens, Mauricio Tec, Claudio Battiloro +2Diffusion ModelsMasked Diffusion Models

    ETH Zürich · Harvard University · MIT

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

    Oct 7, 2026Hanqiu Li Cai, Chema GarabitoT2I Diffusion ModelsPixel-Space Diffusion Models

    SperidLabs

  15. Are Parameter-Efficient Fine-tuning Methods Really Different?

    Oct 6, 2026Yikuan Li, Pinyan Lu, Fanghui LiuParameter-Efficient Fine-TuningLow-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.

  16. MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models

    Oct 6, 2026Syed Ibrahim Omer, Ginny Y. Wong, Xiangyu ZhaoState Space ModelsDiffusion Model Fine-Tuning

    Department of Data Science, City University of Hong Kong · NVIDIA AI Technology Center, NVIDIA, Santa Clara, USA

  17. LiDAR Resolution Recovery via Foundation-Model-Guided Diffusion

    Oct 6, 2026Samed Doğan, Nico Leuze, Alfred SchöttlDiffusion Model GuidanceDepth Completion

    Dept. of Electrical Engineering and Information Technology Munich University of Applied Sciences, 80335 Munich, Germany

  18. Adapting a Latent Audio Diffusion Model to Historical Guqin Recordings: A Listening-Driven Case Study

    Oct 5, 2026Huanchen CaiText-to-Music GenerationMusic Generation Evaluation

    Division of Speech, Music and Hearing (TMH) KTH Royal Institute of Technology, Stockholm, Sweden

  19. Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation

    Oct 5, 2026Wenxuan Wang, Zekai Liu, Weinan Zhang +2T2I Diffusion ModelsContext Distillation

    Harbin Institute of Technology · Shanghai AI Laboratory · Shandong University +2

  20. Protecting Sensitive Data in Image Synthesis via PAC-Private Adaptation for Diffusion Models

    Oct 2, 2026Boming Miao, Tao Zhang, Netanel Raviv +3Privacy-Preserving MLDiffusion-Based Image Generation

    Department of Computer Science and Engineering, Washington University in St. Louis

  21. IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion Models

    Oct 2, 2026Vladislav Gromadskii, David Li, Samson Gourevitch +4Diffusion Model Fine-TuningMasked Diffusion Models

    Applied AI Institute, Moscow, Russia · MBZUAI · CMAP, École Polytechnique +3

  22. CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork

    Oct 1, 2026Wojciech Gromski, Patryk Krukowski, Jan Miksa +2Subject-Driven Image GenerationT2I Generation

    Wrocław University of Science and Technology · IDEAS Research Institute · Jagiellonian University, Krak´ow +2

  23. Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models

    Sep 30, 2026Maksim Bobrin, Maksim Zhdanov, Dmitry DylovDiffusion Model AlignmentConstrained Generative Modeling

    AXXX · Applied AI Institute · MBZUAI

  24. CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models

    Sep 30, 2026Shu Yu, Chaochao LuDiffusion Model Fine-TuningCompositional T2I Generation

    Shanghai Artificial Intelligence Laboratory, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Fudan University, Shanghai, China

  25. ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

    Sep 30, 2026Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah +1Diffusion Model GuidanceClassifier-Free Guidance

    University of Illinois Urbana-Champaign

  26. Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting

    Sep 29, 2026Loay Mualem, Lluís Pastor-Pérez, Vinh Tong +4Masked Diffusion ModelsDiffusion Model Fine-Tuning

    IMPRS-IS · Institute for AI, University of Stuttgart · Bitdefender

  27. ExploreNet: Learning Where to Explore in Diffusion GRPO

    Sep 29, 2026Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov +1Diffusion Model Fine-TuningRL Exploration

    University of Washington

  28. Adversarial Training for Pixel Diffusion

    Sep 29, 2026Xin Lin, Zhifei Zhang, Yuqian Zhou +4Adversarial TrainingPixel-Space Diffusion Models

    UC San Diego · Adobe Research · Work done during an internship at Adobe Research +1

  29. On Trajectory-Aware Training for Masked Diffusion Language Models

    Sep 29, 2026Manuel Madeira, Amitis Shidani, Alice Bizeul +6Masked Diffusion ModelsDiffusion Language Model Inference

    EPFL · Apple · Georgia Institute of Technology

  30. MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators

    Sep 29, 2026Haocheng Tang, Tianchi Xie, Xingqiao LinFlow MatchingMeanFlow

    Northeastern University Boston, MA 02115, USA · Tsinghua University Beijing, 100084, PRC · Carnegie Mellon University Pittsburgh, PA 15213, USA