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

Aug 1, 2026cs.GR

NuclearDiffusion: Text-to-Image Foundation Models for Learning Nuclear Energy Concepts

Generative artificial intelligence (AI) has transformed text-to-image synthesis, yet its ability to represent specialized engineering domains remains largely unexplored. As an exmaple in nuclear engineering, general-purpose foundation models frequently generate physically incorrect or conceptually inconsistent images because they lack domain-specific knowledge. This work presents one of the first systematic studies of domain adaptation for nuclear text-to-image generation through fine-tuning of open-source diffusion models. We curate a dataset of 1,000 captioned nuclear energy images spanning reactors, fuel cycles, radiation, and related concepts, and use it to fine-tune three state-of-the-art open-source models: Stable Diffusion XL (SDXL), SD-v3.5-Medium, and the flow-matching Flux.1 model. Their performance is evaluated using both quantitative image-similarity metrics and qualitative expert assessment against the corresponding zero-shot models. Fine-tuning substantially improves the fidelity of SDXL, provides only limited gains for SD-v3.5-Medium, and yields no measurable improvement for Flux.1, demonstrating that adaptation effectiveness depends strongly on the underlying generative architecture rather than model scale alone. We further compare the fine-tuned models against three leading commercial systems--GPT-Image-2, Gemini-3.1-Flash-Image, and Midjourney. Although GPT-Image-2 and Gemini generate convincing images for broad nuclear concepts, they frequently fail on specialized engineering prompts, where the fine-tuned open-source models produce more accurate and technically consistent outputs. These results establish domain-specific fine-tuning as a practical pathway for developing trustworthy generative AI tools for domain-specific applications.

Mohammed I. Radaideh, Jeremy Moon, Andre Gala-Garza +3

Department of Mechanical Engineering, University of Michigan, Ann Arbor, Michigan 48109, USA · Michigan Institute for Computational Discovery and Engineering (MICDE), University of Michigan, Ann Arbor, Michigan 48109, USA · Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan 48109, USA +1

Domain Adaptation Diffusion Model Fine-Tuning T2I Generation Evaluation

Aug 1, 2026cs.CV

CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds

Recent subject-to-image models have achieved impressive progress in personalized image generation, yet they still struggle to preserve fine-grained subject-specific details. A major reason is the lack of high-quality fine-grained identity supervision: real paired data are expensive to collect, while synthesized training pairs often preserve only coarse subject appearance and fail to capture subtle subject-specific details. In this work, we propose CopyCat, a lightweight model-refinement framework that improves fine-grained subject consistency within only a few seconds. CopyCat performs a one-time refinement of a pretrained subject-to-image model by attaching a lightweight Fine-grained Consistency LoRA (FCLoRA) and optimizing it using a single proxy image, which is used as both the conditioning image and the reconstruction target. This exact self-reconstruction objective substantially simplifies the optimization task, enabling effective fine-grained refinement within only a few seconds. The refinement is performed only once; the resulting model can be directly applied to diverse unseen reference subjects and prompts without further subject-specific optimization. We further revisit subject-to-image LoRA training in double-stream diffusion transformers and find that adapting only the visual stream consistently improves subject consistency. Extensive experiments on DreamBench and XVerseBench demonstrate consistent improvements in fine-grained subject consistency across representative subject-to-image models under both single- and multi-subject settings.

Peng Zheng, Ruiqi Liu, Rui Ma +1

School of Artificial Intelligence, Jilin University · 2Shanghai Innovation Institute · 4Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China +1

Diffusion Transformer Subject-Driven Image Generation Image Generation Diffusion Model Fine-Tuning

Jul 31, 2026cs.CL

DiffusionGemma Technical Report

We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottleneck of conventional autoregressive (AR) large language models. Instead of training from scratch, we obtain DiffusionGemma by fine-tuning the mixture-of-experts Gemma 4 model with 3.8B activated and 25.2B total parameters. Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget. The first stage uses supervised fine-tuning to teach bidirectional denoising, while the second stage combines reinforcement learning with sampler distillation to jointly improve generation quality and inference efficiency. DiffusionGemma establishes a new Pareto frontier for the trade-off between generation speed and model capability. Averaged across our full evaluation suite, it generates around 20 tokens per forward pass and achieves roughly 1,500 output tokens per second on a single NVIDIA H100 GPU, which is substantially faster than AR models even with state-of-the-art speculative decoding. DiffusionGemma also retains the starting model's support for thinking mode, multimodal inputs, and long contexts. Despite diffusion fine-tuning, it remains capable of AR generation with only minor performance degradation, suggesting a path toward hybrid diffusion-AR decoding.

DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41

Blockwise Diffusion Language Models Diffusion Model Fine-Tuning Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration

Jul 28, 2026cs.CV

ScaleResfusion: Residual Rectified Flow based on Residual Vector Field

Real-world Image Restoration (Real-IR) aims to recover high-quality (HQ) images from complex and unknown degradations. Recent diffusion-based methods have substantially improved perceptual quality, yet two obstacles remain: methods that sample from Gaussian noise require many steps and are often less faithful to the degraded input, whereas residual-based methods that start from the low-quality (LQ) image typically train task-specific models from scratch, with optimization objectives coupled to a particular noise scheduler, and therefore cannot reuse modern pre-trained generative priors. We present \textbf{ScaleResfusion}, which rewrites residual restoration as a scheduler-independent adaptation interface for pre-trained text-to-image rectified-flow models. Its core, \textbf{Residual Rectified Flow} (RRF), inserts the residual term

R

into the linear transport path of Rectified Flow, so that sampling starts from noisy LQ at an exact acceleration point, where the signal-to-noise ratio of the starting state is continuously controlled by the residual ratio

γ

. The resulting optimization target, the \textbf{residual vector field}, contains no scheduler-specific coefficients and differs from the pre-trained rectified-flow target only by the residual offset

γR

; adapting a frozen billion-scale backbone therefore reduces to fitting this compact residual correction with LoRA-only training. A knowledge-distillation pipeline built around RRF further reduces sampling to as few as 4 steps. Experiments on real-world super-resolution across multiple benchmarks show that ScaleResfusion achieves state-of-the-art restoration quality and transfers consistently across pre-trained rectified-flow backbones from 2B to 9B parameters.

Zhenning Shi, Chen Xu, Junhao Zhang +4

College of Computer Science, Nankai University, Tianjin, China · Faculty of Information Science and Computing, University of Macau, Macau, China · CSIRO Data61, Australia +1

Diffusion Models for Image Restoration Rectified Flow Diffusion Model Fine-Tuning Diffusion-Based Inverse Problems Image Super-Resolution

Jul 28, 2026cs.AI

PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention

Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising. We study this problem at the level of attention rather than claiming AR-weight reuse itself as novel. PreDiff-LM preserves causal attention within the observed prompt while allowing full bidirectional attention within the masked target. Under a matched GPT-2 Medium, WikiText-103, 90K-step setup, this hybrid mask improves unconditional perplexity from 34.1 to 28.7 and MAUVE from 0.71 to 0.78 over uniform bidirectional attention with the same AR initialization. Attention adaptation also composes with a DiffuGPT-style objective adaptation, reaching 26.9 perplexity. Pretrained initialization reduces the steps required to reach perplexity below 50 from about 350K to 8K, although a compute-matched fine-tuned AR model remains stronger at equal scale (18.9 versus 28.7). Beyond perplexity, PreDiff-LM improves repetition, distributional quality, four zero-shot downstream tasks, and human preference over prior diffusion baselines. The results position hybrid attention as a complementary mechanism for adapting pretrained causal backbones, while making explicit the remaining quality and inference-efficiency gaps to optimized AR models.

Zhengtao Yao, Runhao Li, Xupeng Chen +12

University of Southern California · New York University · Columbia University +4

Masked Diffusion Models Attention Control in Diffusion Models Diffusion Model Fine-Tuning Diffusion Language Models

Jul 23, 2026cs.AI

Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model Finetuning

Fine-tuning large diffusion models for new domains or styles involves a trade-off: improving target-specific generation often degrades the pretrained model's broad generative capability. Existing full and parameter-efficient fine-tuning methods typically handle this trade-off only implicitly. In this work, we propose a novel source-prior-driven selective adaptation method to efficiently fine-tune diffusion models, achieving a favorable trade-off. Our method relies on two key observations: (1) the loss of general generative capability is highly inconsistent across pretrained parameters, and (2) parameters that have a relatively small impact on the model's general generative capability remain structurally inconsistent across layers and parameter types. Motivated by these observations, we first learn a static mask to explicitly identify parameters better suited for downstream adaptation, and then construct structured update strategies for the selected subset. Experiments show that our method achieves a better adaptation-retention trade-off than existing strong baselines.

Yi Xiong, Yuan-Yuan Cheng, Xiao-Ming Fu

University of Science and Technology of China, China

Fine-Tuning Diffusion Model Fine-Tuning Selective Fine-Tuning Parameter-Efficient Fine-Tuning Catastrophic Forgetting

Jul 17, 2026cs.CV

MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion

High-resolution video diffusion models built on Diffusion Transformers (DiTs) deliver strong fidelity but quickly exhaust the memory budget of a single workstation. A 100 billion-plus parameter DiT easily requires over a terabyte of persistent state, while naive spatiotemporal self-attention grows quadratically in sequence length. These two walls -- parameter memory and activation memory -- prevent researchers from adapting massive generative models without large GPU clusters. We revisit this problem from a systems perspective and introduce MegaSlide-DiT, a prototype that demonstrates how a pre-trained 105B DiT can be adapted on a single H200 GPU with 1.5 TB of host RAM. Our key insight is that the GPU need not own the model state: all persistent weights, master weights and optimizer moments remain in host memory, while only transient shards are streamed to the GPU on demand. Simultaneously, we replace quadratic global attention with 3D Deformable Slide Attention (3D-DSA), a motion-adaptive local attention operator that reduces both memory and computational complexity to linear in the sequence length. We report detailed memory accounting, execution traces and evaluation results to substantiate our design. MegaSlide-DiT does not claim to train a 105B model from scratch on a single GPU, nor does it magically solve bandwidth limits; rather, it offers a pragmatic path for full-parameter adaptation of massive video diffusion models on high-end workstations.

Jiacheng Liu, Jason Liu

Trendinsight Lab / UC San Diego

Video Diffusion Models Diffusion Transformer Diffusion Model Fine-Tuning Deformable Attention Memory-Efficient Training

Jul 16, 2026cs.CV

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

Large-scale video diffusion models (VDMs) deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational costs. Existing parameter-efficient fine-tuning (PEFT) methods have two critical flaws on billion-scale models: they still require substantial trainable parameters, and reward-based training suffers from noise-induced optimization instability in condition-guided tasks. We propose MagicPrompt, a lightweight framework that achieves extreme parameter efficiency and stable reward optimization. It first adopts Attention-Embedded Prompt Tuning, which steers generation via lightweight soft prompts with orders of magnitude fewer parameters while preserving pre-trained knowledge. It further introduces Dual-Space Reward Feedback Optimization, which uses self-supervised latent objectives to improve condition-guided reward training. Experiments show MagicPrompt reaches competitive performance with less than 1% trainable parameters and notably reduces training costs.

Yinhan Zhang, Dinwei Tan, Xianghao Kong +3

HKUST · Tencent · HKUST(GZ)

Video Diffusion Models Diffusion Model Fine-Tuning Visual Prompt Learning

Jul 16, 2026cs.LG

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a complete continuous-time RL framework for fine-tuning score-based discrete diffusion models. The proposed framework enables reward-driven optimization without requiring differentiability on the reward signals. In contrast to the existing GRPO-based approaches that only rely on terminal rewards, our formulation allows intermediate reward or advantage signals to be incorporated throughout the denoising trajectory. Importantly, when specialized to masked diffusion models (MDMs), our framework encompasses a rich class of policy parameterizations over the vocabulary simplex with analytically tractable probability ratios, providing a unified perspective on exploration and policy optimization in MDMs. For masked diffusion large language models (dLLMs), we further propose trajectory subsampling techniques to efficiently estimate computationally prohibitive trajectory likelihoods, reducing the computational cost of computing per-position probability ratios. We showcase the effectiveness of our methods on both low-dimensional entropy-regularized optimization problems and RL post-training of dLLMs on mathematical reasoning and coding tasks.

Zikun Zhang, Jiayuan Sheng, David D. Yao +1

Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027

Masked Diffusion Models RL for Language Model Reasoning Diffusion Model Fine-Tuning Continuous-Time RL RL for Diffusion Models Diffusion Language Models

Jul 15, 2026cs.LG

Integration Matters: Rollout-Based Training for Constrained Diffusion Models

Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods.

Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg +1

University of British Columbia · Inverted AI · Alberta Machine Intelligence Institute

Constrained Generative Modeling Diffusion Sampling Diffusion Model Fine-Tuning Diffusion Models

Jul 14, 2026cs.CV

Improving Medical Image Generative Models with Fréchet Distance Loss

Diffusion generative models have demonstrated immense potential for synthetic medical image generation. However, these models often struggle to capture complex morphological characteristics of heterogeneous tumors with irregular boundaries, limiting their utility for downstream clinical tasks such as segmentation. This limitation stems from the standard denoising objective: minimizing a per-pixel error, which smooths high-variance irregular structures characteristic of tumors. To address this, we propose finetuning these generative models with Fréchet Distance loss (FD-loss). FD-loss aligns the first and second order feature statistics of real and generated images in a pretrained encoder space, encouraging the generator to capture complex structural variations characteristic of heterogeneous tumors. We integrate FD-loss across diverse architectural settings, using both natural- and medical-image encoders on multiple liver and brain cancer datasets spanning CT and MRI modalities. Downstream segmentation networks trained on our FD-regularized synthetic data consistently achieve superior performance, improving tumor DSC by

>$$5\%

over unregularized synthetic augmentation alone. Qualitative analysis suggests these gains are associated with more faithful tumor synthesis and fewer segmentation hallucinations. Our results show FD-loss as an effective regularizer for medical image generative models to improve clinical workflows.

Andrew Marshall, Xuanang Xu, Xiaoran Zhang +3

Department of Biomedical Engineering, Yale University · Department of Radiology & Biomedical Imaging, Yale University · Department of Electrical Engineering, Yale University

Synthetic Data Augmentation Distribution Matching Diffusion Model Fine-Tuning Medical Image Synthesis

Jul 14, 2026cs.CV

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task. Existing approaches largely improve synthetic data by increasing realism, diversity, or domain adaptation, while overlooking a more fundamental question: how should sample usefulness for classification be measured and optimized? We address this with Class-Contrastive Influence (C2I), a criterion that quantifies a sample's usefulness through its gradient-based influence on the classifier. We find that effective samples exhibit a strong C2I gap: their loss gradients align with validation gradients from the same class and oppose those from other classes. Our analysis further suggests that such high-C2I samples are hard, boundary-proximal examples that help refine the decision boundary and improve robustness. Building on this insight, we fine-tune diffusion models with reinforcement learning using a C2I-based reward to steer generation toward class-informative samples. Across several few-shot medical imaging benchmarks, C2I-guided generation improves downstream accuracy and robustness over diffusion-based augmentation baselines, showing that synthetic augmentation is most effective when guided by task usefulness rather than image quality alone.

Jeeyung Kim, Erfan Esmaeili, Qiang Qiu

Purdue University, West Lafayette, USA

Synthetic Data Augmentation Diffusion Model Fine-Tuning Diffusion-Based Image Generation

Jul 10, 2026cs.CV

Probing Diffusion Denoising Dynamics for Contrastive Representation Learning

Text-to-image diffusion models exhibit unprecedented generative capability and contain rich intermediate representations that can be useful for discriminative vision tasks. Motivated by this observation, we study a focused question: how can the denoising dynamics of a pretrained diffusion model be adapted to support discriminative representation learning while preserving its generative behavior under parameter-efficient updates? We present D

^3

CL as an investigation of this question. Our key observation is that noisy latents at different diffusion timesteps can be interpreted as stochastic views of the same underlying image, enabling a contrastive objective to be coupled with the standard denoising reconstruction loss. This formulation provides a simple way to probe the interaction between generative denoising and discriminative representation learning without training from scratch. To keep the adaptation lightweight, we apply LoRA updates to a pretrained Stable Diffusion backbone while freezing the original model parameters. D

^3

CL provides strong empirical evidence that reconstruction and noise-level contrastive objectives can be complementary: on ImageNet-1K, it obtains 80.1% linear-probing accuracy and an FID of 5.56 for

256 \times 256

unconditional generation. Additional ablations on the design space suggest that the usefulness of diffusion features depends on where and how denoising states are sampled. These results establish D

^3

CL as a parameter-efficient adaptation framework for pretrained diffusion models, showing that noise-level contrastive learning can structure denoising representations for discriminative tasks while maintaining generative performance.

Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal +1

Australian National University · CSIRO Data61 · Amazon

Contrastive Learning Diffusion Model Fine-Tuning Diffusion Models Image Classification

Jul 7, 2026cs.LG

TILDE: TILt-based Distributional Erasure for Concept Unlearning

Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each prompt. We instantiate this principle with residual

\nabla

-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.

Naveen George, Naoki Murata, Yuhta Takida +2

Indian Institute of Technology Hyderabad · Sony AI · Sony AI & Sony Group Corporation

Diffusion Model Fine-Tuning Diffusion Model Unlearning Concept Erasure T2I Diffusion Models

Jul 7, 2026cs.LG

FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models

Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow training speed, which existing parameter-efficient fine-tuning methods only partially address. To overcome these limitations, we propose FourTune, an efficient post-training framework for diffusion models based on an end-to-end W4A4G4 paradigm. FourTune introduces a triple-branch hybrid pipeline that augments the standard LoRA architecture with a frozen numerical stabilizer to isolate quantization-sensitive outliers, enabling stable training under native 4-bit computation. In addition, FourTune employs hardware-efficient block-wise quantization and customized fused kernels to support efficient quantized backpropagation and reduce memory bandwidth overhead. Across customization, reinforcement learning, and distillation tasks, FourTune matches the quality of full-precision fine-tuning. On FLUX.1-dev (12B), FourTune reduces memory overhead by 2.25

\times

and increases end-to-end training throughput by 2.27

\times

compared to BF16 LoRA.

Bowen Xue, Zihan Min, Xingyang Li +8

Nunchux AI · MIT · Stanford +2

Diffusion Model Quantization Quantization-Aware Training Diffusion Model Fine-Tuning Low-Bit Quantization Diffusion Models Parameter-Efficient Fine-Tuning

Jul 6, 2026cs.CV

LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models

Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independently trained concept adapters in a shared weight space (via federated averaging, gradient fusion, or orthogonality constraints) suffer from identity confusion and style bleeding. In this work, we show that composing concepts as separate image layers, instead of merging their adapters in a shared weight space, avoids parameter-level interference. We introduce LILAC, a framework that composes independently trained low-rank adapters at inference time: each subject is conditioned on the frozen composite of previously placed subjects, with exactly one adapter active at a time, therefore identities never interfere at the parameter level. LILAC composes the adapters without joint training, scales linearly with the number of concepts, and is backbone-agnostic. Under the Orthogonal Adaptation protocol, LILAC applied on Qwen-Image-Edit+Qwen-Image-Layered reaches an ArcFace detection rate of 0.861. Code is available at https://github.com/marianlupascu/LILAC.

Marian Lupascu, Sebastian Ripa, Mihai Trascau +2

Adobe Research, Romania · International Computer High School of Bucharest, Romania

Subject-Driven Image Generation Compositional Image Generation Diffusion Model Fine-Tuning Low-Rank Adaptation T2I Diffusion Models

Jul 5, 2026eess.AS

DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech

Autoregressive (AR) text-to-speech (TTS) models generate discrete speech tokens sequentially, which makes inference slow and can degrade robustness by propagating local errors and hallucinations. This limitation stems from their left-to-right AR commitment: each token must be determined before future speech-token context is available. However, such ordering is not an inherent requirement for TTS, as the full input text is available before synthesis. In this paper, we introduce DELTA-TTS, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffusion language model (dLLM) for confidence-ordered speech-token decoding. To better capture the local structure of speech, DELTA-TTS incorporates a convolution module that injects local acoustic context, together with a

1/t

-weighted training objective and a time-shifted inference schedule that defer low-confidence positions to later steps. Trained on only

585

hours of LibriTTS, DELTA-TTS achieves a

\textbf{1.75}\%

WER on Seed-TTS test-en, outperforming its AR backbone while generating tokens

\textbf{3.3}\times

faster. Further analysis shows that DELTA-TTS produces sharper text--speech alignment, increases overall decoding confidence, and mitigates hallucinations observed in AR generation.

Junwon Moon, Seungbeom Kim, Yejin Lee +4

1Sungkyunkwan University · University of Seoul

TTS Synthesis Diffusion Model Fine-Tuning Diffusion Language Model Decoding Diffusion Language Models Audio Generation

Jul 4, 2026cs.CV

Self-Improving Diffusion Classifiers with Minority Preference Optimization

Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance. However, their effectiveness is strongly tied to the pretraining data distribution: they perform well in majority, high-density regions of the data manifold, but are significantly less accurate in minority, low-density regions. Although prior works on minority sampling have focused on generating more minority-like images, what minority sampling fundamentally enables beyond generation remains underexplored. In this paper, we reveal a direct relationship between minority sampling in generation and the perception capability of diffusion classifiers. Specifically, we show that enhancing minority sampling broadens the coverage of underrepresented regions on the data manifold, thereby improving diffusion-based recognition. To exploit this connection, we propose \textit{Self-Improving Diffusion Classifiers with Minority Preference Optimization} (MiPO), which fine-tunes a pretrained diffusion model using minority preference rewards. Using only arbitrary caption data, MiPO generates candidate samples, rewards those that better cover minority regions, and optimizes the model with LoRA and Group Relative Policy Optimization, without additional image data, external foundation models, or external reward models. This enables stable, prompt-adaptive minority sampling and translates low-density generative coverage into improved zero-shot diffusion classification. To sum up, we show that diffusion classifier perception is biased toward majority regions, demonstrate that this bias can be alleviated through minority preference optimization, and evaluate MiPO on five standard datasets.

Hyunsoo Kim, Jungmyung Wi, Soobin Um +2

1Korea University · 2Kook Min University · 3Kyung Hee University

Diffusion Model Alignment Long-Tailed Classification Diffusion Model Fine-Tuning RL for Diffusion Models Zero-Shot Image Classification

Jul 3, 2026cs.LG

On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures. At test time, however, the goal is not to sample from this prior, but to use a limited oracle budget to shift generation toward task-specific high-reward molecules. We study this adaptation problem for discrete diffusion models. Each online round couples several choices. The loop must decide which candidates to evaluate, how rewards become model updates, which feedback to reuse, and how far to move beyond the pretrained prior. These choices have mostly been studied in isolation, leaving open whether they complement one another, become redundant, or interfere inside a full online adaptation loop. We conduct controlled studies across six small-molecule binding-affinity tasks and three protein-fitness tasks. We find that acquisition, reward shaping, and model debiasing provide complementary routes to higher reward, especially for small molecules. Replay further stabilizes learning, while validity penalties keep small-molecule exploration on the valid molecular manifold. Together, these findings point to a practical recipe for feedback-efficient molecular optimization: online fine-tuning with acquisition, reward shaping, debiasing, replay, and validity control. This recipe outperforms offline fine-tuning and inference-time search baselines under matched oracle-call budgets and GPU-hour accounting. The gains are largest when high-reward candidates require larger shifts from the pretrained prior.

Trevor Chen, Ariel Dai, Jason Yang +8

1Caltech · ETH Zurich · ETH AI Center +1

Molecular Optimization Diffusion Model Fine-Tuning Diffusion Models

Jul 2, 2026cs.LG

Optimizing Visual Generative Models via Distribution-wise Rewards

Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies. To address these limitations, we present a novel framework that finetunes generative models using distribution-wise rewards, ensuring better alignment with real-world data distributions. Unlike rewards that evaluate samples individually, distribution-wise reward accounts for the data distribution of the samples, mitigating the mode collapse problem that occurs when all samples optimize towards the same direction independently. To overcome the prohibitive computational cost of estimating these rewards, we introduce a subset-replace strategy that efficiently provides reward signals by updating only a small subset of a generated reference set. Additionally, we apply RL to optimize post-hoc model merging coefficients, potentially mitigating the train-inference inconsistency caused by introducing stochastic differential equation (SDE) in regular RL practices. Extensive experiments show our approach significantly improves FID-50K across various base models, from 8.30 to 5.77 for SiT and from 3.74 to 3.52 for EDM2. Qualitative evaluation also confirms that our method enhances perceptual quality while preserving sample diversity.

Ruihang Li, Mengde Xu, Shuyang Gu +4

University of Science and Technology of China · Shanghai Innovation Institute · Hunyuan Frontier Lab, Tencent +1

Diffusion Model Fine-Tuning RL for Image Generation RL for Generative Models Mode Collapse

Jul 1, 2026cs.LG

PAPA: Online Personalized Active Preference Alignment

Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized recommender systems, the objective often shifts to modeling specific regions of the distribution that maximize user preferences-initially unknown but gradually uncovered through interactive feedback. This can naturally be framed as a reinforcement learning problem, where the goal is to fine-tune a diffusion model to maximize a reward function based on preferences. However, the main challenge lies in learning a parameterized reward model, which typically requires large-scale preference data-something that is often not feasible in practice. In this work, we introduce Personalized Active Preference Alignment PAPA, a novel method that bypasses the requirement for a parametrized reward model by directly optimizing the diffusion model using real-time user feedback. PAPA enables feedback-efficient preference alignment, drawing inspiration from the variational inference framework. We demonstrate PAPA's effectiveness through extensive experiments and ablation studies across diverse class-conditioned and fine-grained alignment tasks. Additionally, based on theoretical insights, we propose an enhanced fine-tuning strategy, referred to as EPAPA, that requires less computational budget and accelerates the fine-tuning process, further boosting PAPA's suitability for real-world deployment. Our code is made publicly available at https://github.com/NasikNafi/papa.

Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas +2

Washington University in St. Louis · Oak Ridge National Laboratory

Diffusion Model Alignment Diffusion Model Fine-Tuning RL for Diffusion Models User Preference Modeling Preference Learning

Jun 30, 2026cs.CL

SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing

Reinforcement learning for diffusion large language models (dLLMs) has largely moved to trajectory-aware methods. The current state of the art, TraceRL, holds that random masking is mismatched with the model's inference trajectory, and it reconstructs that trajectory during training by slicing each rollout into up to K/s trajectory-aligned training samples, a cost that grows with the block size K. We show that this mismatch can be mitigated without reconstructing the trajectory. Our method, SLIM-RL, bounds the commit risk of each rollout step with a tau-budget decoder, reducing aggregate commit risk in the training data. During optimization, SLIM-RL trains on these risk-controlled rollouts with a trace-free random-masking objective that adapts variance-reduction tools, combining sequence-level importance sampling, deterministic quadrature over masking levels under a mean-preserving, monotonically decreasing per-block mask schedule that we introduce. On SDAR-4B, SLIM-RL matches TraceRL's best MATH500 accuracy on only 0.46x its training samples at block size 16, improving over TraceRL by 6.32% on MATH500 and 11.05% on GSM8K under matched dynamic sampling. At block size 4, the 4B SLIM-RL surpasses the larger LLaDA-8B and Dream-7B dLLMs on math, exceeding LLaDA-8B by 10.76% on MATH500 while staying below the autoregressive Qwen2.5-7B. On code, it improves over TraceRL by 4.20% on MBPP and 3.65% on HumanEval. The tau-budget decoder transfers training-free across LLaDA, Dream, and SDAR. The source code is available at https://github.com/laolaorkkkkk/SLIM-RL .

Ruikang Zhao, Zhenting Wang, Han Gao +1

Technical University of Denmark · MBZUAI Institute of Foundation Models · Iowa State University +1

Reinforcement Learning RL for Language Model Reasoning Diffusion Model Fine-Tuning RL for Diffusion Models Diffusion Language Models

Jun 29, 2026cs.LG

Diffusion Fine-tuning with Rewarded Moment Matching Distillation

Distillation and Reinforcement Learning (RL) fine-tuning are the primary pillars of diffusion post-training. While traditionally studied in isolation, the interaction between these phases remains poorly understood, and in particular how fine-tuning impacts the generative quality of distilled models. We introduce Rewarded Moment Matching Distillation (RMMD), a novel framework that simultaneously distills diffusion models and maximizes a reward function. RMMD preserves the high-fidelity ``naturalness'' characteristic of advanced distillation (such as 8-step Moment Matching) by adapting the sampling loop for on-policy training and repurposing the distillation loss as a proxy for integral KL regularization. By evaluating the FID-Reward Pareto fronts on ImageNet, we demonstrate that RMMD achieves superior trade-offs compared to single-step baselines (DI++) and multi-step competitors (DRaFT, HyperNoise). Finally, we apply RMMD to GenCast, a state-of-the-art weather forecasting model, to distill it while optimizing the Continuous Ranked Probability Score (CRPS) metric. The resulting distilled model achieves a 7.5x speedup while outperforming the teacher model on 93% of target weather variables, and being better calibrated. This proves that RMMD scales to complex, high-dimensional scientific domains.

Alexis Jacq, Guillaume Couairon, Valentin De Bortoli +3

1Google DeepMind

Diffusion Model Distillation Diffusion Model Fine-Tuning RL for Diffusion Models

Jun 26, 2026cs.CV

SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models

Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic failure, "motion entanglement", the unintended coupling of independent motion sources, such as camera movement and object motion. We identify that this issue stems from data bias and the reconstruction-based training design of diffusion models. Training on noisy videos that still retain coarse motion cues inadvertently encourages the model to replicate existing motion without an incentive to learn how to model kinematically-grounded motions. To address this, we propose a Self-Imagination Fine-Tuning (SIFT) paradigm, which enables the model to learn from its own generated videos rather than directly reconstructing real ones, breaking the reconstruction shortcut. We further employ motion-aware discriminative supervision and a progressive hard-case replay strategy to stabilize and accelerate learning. By leveraging freely-generated text prompts, our method can densely cover a broad motion space, including rare or finely-disentangled scenarios that would be costly to collect as video data. Extensive experiments demonstrate that our approach substantially improves the physical realism, motion disentanglement, and controllability of generated videos.

Ruoyu Wang, Jialun Liu, Huayang Huang +5

School of Computer Science, Wuhan University · Institute of Artificial Intelligence, China Telecom (TeleAI) · School of Artificial Intelligence, Wuhan University

Physical Consistency in Video Generation Video Diffusion Models Diffusion Model Fine-Tuning Diffusion Models for Motion Generation Controllable Video Generation

Jun 23, 2026cs.LG

When Top-1 Fails: Calibrating LoRA Monitors for Masked Diffusion LMs

Discrete diffusion language model (DLM) fine-tuning inherits inexpensive diagnostics from denoising-time confidence monitors, but their PEFT-training meaning is untested. We test top-1 argmax concentration as a collapse warning. Across 816 LoRA/PEFT configurations from three DLM families, the warning fires for every configuration while logs record 0/816 actual collapses at the 200 step horizon, giving zero precision. The cause is pre-equilibrium saturation: top-1 concentration is already high before optimization and quickly becomes insensitive to final training stability. We then evaluate max LoRA gradient norm, a parameter-side signal that samples gradient routing rather than token concentration. On a pooled held-out LLaDA-family split, a train-optimized threshold identifies top-decile final-loss configurations with precision 0.68 and F1=0.79, above the all-positive top-1 baseline even at the lower split-bootstrap confidence bound. Autoregressive controls and cross-family threshold failures bound the result to short-horizon DLM-LoRA inspection rather than a universal collapse detector. Workflow: drop top-1 as a PEFT alarm, log max-gradient early in training, and calibrate thresholds per DLM family before routing runs for inspection.

Lucky Verma, Pratik Yadav

Independent Researcher · University of Maryland, Baltimore County

Diffusion Model Fine-Tuning Diffusion Language Models Neural Network Training Dynamics Parameter-Efficient Fine-Tuning

Jun 22, 2026cs.CV

Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping

Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However, these models are computationally expensive in runtime, and their cost scales severely with the number of input references. While the efficiency of diffusion models has been extensively studied in the context of prompt-driven generation, it remains largely under-explored in the realm of reference-based models. This setting presents unique challenges not addressed by methods focusing solely on generation. In particular, the wasteful representation of references as dense token grids offers significant opportunities for improvement. In this work, we present Sparse Context, a method for constructing sparse reference representations by retaining only a reduced subset of reference tokens. We observe that even without modifying the model, dropping a significant portion of reference tokens at inference time largely preserves its generation capabilities. To fully realize this potential, we fine-tune the model with random token dropping at varying ratios, encouraging robustness to partial reference representations. Crucially, this training strategy decouples the model from any specific token selection rule, allowing flexible control at inference time. At inference time, instead of random dropping, we apply task-aware token selection strategies that prioritize the most informative regions of the reference images, adapting the token budget to the input and task requirements. Extensive experiments show our method achieves a 4x increase in inference speed for multi-reference generation and an 2x for single reference generation. Importantly, this efficiency is achieved without compromising visual quality across both spatially-aligned editing and subject-driven generation.

Rishubh Parihar, Ayush Raina, R. Venkatesh Babu +1

1IISc Bangalore · 2Tel Aviv University

Conditional Image Generation Diffusion Model Fine-Tuning Token Pruning Diffusion-Based Image Editing Diffusion Model Inference Acceleration

Jun 15, 2026cs.CL

Self-Generated Error Training for Token Editing in Diffusion Language Models

Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

Lin Yao

School of Computer Science, Shanghai Jiao Tong University, Shanghai, 200240, China · Zhongguancun Academy, Beijing, 100097, China

LLM Self-Correction Diffusion Model Fine-Tuning Diffusion Language Model Decoding Diffusion Language Models Language Model Editing

Jun 15, 2026cs.CL

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

While reasoning on autoregressive (AR) models is often performed by chain-of-thought reasoning and reflection, their refinement of previous outputs still relies on fully sequential generation, even when only local edits are needed. In contrast, the masking mechanism in Mask Diffusion Models (MDMs) naturally supports explicit local edits on previous outputs, allowing selective refinement without discarding previous answers and generating another from scratch. While this property more closely aligns with how humans correct mistakes by iterative local refinement, existing MDMs do not support multi-turn masking and denoising. We propose Reflective Masking (RM), which elicits such an intrinsic reasoning capability in MDMs via lightweight post-training. RM provides a native test-time scaling, where an MDM iteratively revisits and revises its prior outputs based on evolving context. To exploit insights from previous turns like AR reasoning, we further introduce History Reference, a parameter-free mechanism that leverages intermediate denoising states during revision. Our approach requires no architectural changes and is easily applicable to existing MDMs. Across diverse tasks and modalities, including text generation, Sudoku, and image editing, Reflective Masking consistently outperforms standard masking-based baselines and demonstrates strong generality, positioning RM as a fundamental primitive for reasoning on MDMs.

Yanming Zhang, Yihan Bian, Jingyuan Qi +3

University of Maryland · Virginia Tech · Intuit +2

Masked Diffusion Models Diffusion Model Fine-Tuning Diffusion Language Models Iterative Refinement Diffusion Models

Jun 11, 2026cs.CV

Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation

While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current practice requires training a separate Low-Rank Adaptation (LoRA) module for each effect, incurring substantial data curation and iterative optimization costs that hinder interactive control. We present Prompt2Effect, a weight-driven hypernetwork that amortizes per-effect training by directly synthesizing effect-specific LoRA weights in a single forward pass. Unlike prior hypernetworks that regress adapter weights purely from semantics, Prompt2Effect is explicitly conditioned on the frozen base model weights, grounding prediction in the structural geometry of each layer. Furthermore, instead of predicting raw LoRA matrices, we introduce an SVD-canonicalized parameterization that resolves factorization ambiguity and stabilizes large-scale synthesis. Extensive experiments demonstrate that Prompt2Effect achieves on-par or superior video quality and effect alignment compared to conventional LoRA fine-tuning, while reducing the computational cost from 56 GPU training hours to 3.3 seconds of hypernetwork inference. When used as initialization for subsequent fine-tuning, our predicted weights further improve final performance and accelerate optimization by approximately 10x.

Xiaomeng Yang, Yanyu Li, Gordon Guocheng Qian +7

1Northeastern University, 2Snap Inc.

Image-to-Video Generation Video Diffusion Models Diffusion Model Fine-Tuning Low-Rank Adaptation Hypernetworks

Jun 11, 2026cs.LG

A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

Discrete diffusion models offer a simple and stable likelihood-based framework for sequence generation, recently extended to any-length settings via token insertion. Principled reward-guided fine-tuning for any-length discrete diffusion, however, remains largely unexplored. We introduce Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding (A2D2), a unified framework for reward-guided fine-tuning of any-length discrete diffusion models via joint optimization of the insertion and unmasking policies together with a quality-based inference schedule. We derive the Radon-Nikodym derivative for the joint insertion-unmasking path measures, enabling theoretically guaranteed convergence to the intractable reward-tilted sequence distribution without requiring target samples. Building on this, we establish unmasking and insertion quality as tractable approaches for minimizing decoding error and introduce the Adaptive Joint Decoding (AJD) loss, which provably yields the optimal path measure that generates the reward-tilted distribution. Empirically, A2D2 improves reward optimization while enhancing generation flexibility and accuracy over prior fixed-length fine-tuning and inference-time guidance methods.

Sophia Tang, Yuchen Zhu, Molei Tao +1

Department of Computer and Information Science, University of Pennsylvania · School of Mathematics, Georgia Institute of Technology · Department of Bioengineering, University of Pennsylvania

Diffusion Model Fine-Tuning Diffusion Language Model Decoding RL for Diffusion Models Diffusion Models