Diffusion Model Alignment

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 131

May 26, 2026cs.LG

Explicit Critic Guidance for Aligning Diffusion Models

Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising trajectories and in realizing stable value-based optimization. We propose a state-aligned latent actor-critic framework for diffusion post-training, in which the diffusion model serves as its own timestep-conditioned value function and predicts values directly on noisy latent states. This enables trajectory-level PPO training, supports stable actor-critic optimization with simple conditioning and value pretraining strategies, and naturally allows the learned critic to be reused for inference-time steering. We further extend the framework to multi-reward optimization, where joint training with complementary rewards helps alleviate reward hacking. Across both UNet- and DiT-based backbones, our method consistently outperforms prior group-relative RL and actor-critic baselines on single-reward and multi-reward benchmarks, while test-time steering provides additional gains in generation quality.

Zhengyang Liang, Qihang Zhang, Ceyuan Yang

University of Toronto · Vector Institute · The Chinese University of Hong Kong

Diffusion Model Alignment Diffusion Model Guidance RL for Diffusion Models

May 26, 2026cs.LG

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise comparisons. This pairwise reduction is limiting when training data naturally contains multiple candidate images for the same prompt, and when continuous reward scores can provide richer information than a single winner-loser label. To address these limitations, we propose Diffusion LAIR, a reward-aware listwise preference optimization method for diffusion models. For each prompt, LAIR converts reward scores across a group of candidate images into centered advantage weights, then optimizes an advantage-weighted regression objective on the implicit reward, defined as the denoising-loss improvement of the current model over a fixed reference model, with a quadratic penalty that regularizes the magnitude of the implicit reward. The resulting objective uses all candidates simultaneously rather than selecting pairs, and remains conservative by explicitly controlling the magnitude of the implicit reward. The LAIR objective admits a bounded closed-form optimum in implicit-reward space, clarifying how the regularization strength controls the magnitude of the preference update. Experiments show that Diffusion LAIR outperforms strong preference optimization baselines on SD1.5 and SDXL across text-to-image generation, compositional generation, and image editing benchmarks.

Austin Wang, Jiaqi Han, Stefano Ermon +1

Caltech · Stanford University

Diffusion Model Alignment Preference Optimization T2I Diffusion Models

May 25, 2026cs.CV

Reinforcing Few-step Generators via Reward-Tilted Distribution Matching

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a two-stage framework that unifies distribution matching distillation with reward-guided reinforcement learning for few-step flow generators. We show that minimizing the KL divergence to a reward-tilted teacher distribution naturally decomposes into a distribution matching term and a reward maximization term. In the first stage, we introduce Ambient-Consistent Distribution Matching Distillation (AC-DMD), which performs subinterval-wise distribution matching and augments the fake score objective with a consistency regularizer to help the fake score model track the shifting generator distribution under limited updates. In the second stage, we jointly optimize both terms: for the reward maximization term, we derive a hybrid policy gradient that combines a GRPO-style estimator for the stochastic intermediate transitions with direct reward backpropagation through the deterministic final step, and further introduce step-subset GRPO (SubGRPO) to reduce variance. Experiments on SD3, SD3.5, and FLUX.2 demonstrate that RTDMD establishes new state-of-the-art results across preference, aesthetic, and compositional metrics with only 4 inference steps, outperforming previous few-step text-to-image generation methods. Code and models are available at https://github.com/Harahan/RTDMD.

Yushi Huang, Xiangxin Zhou, Ruoyu Wang +3

Tencent Hunyuan · Hong Kong University of Science and Technology · Westlake University

Diffusion Model Alignment Diffusion Model Distillation Few-Step Diffusion Sampling RL for Diffusion Models Distribution Matching Distillation T2I Diffusion Models

May 25, 2026cs.CV

AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis

Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the denoising process. Existing works primarily focus on inter-subject-token activations (i.e., cross-attention scores) overlap for different subjects, overlooking the intra-subject-token activations scattering issue for identical subjects. In this paper, we propose an Aggregating-and-Isolating cross-attention approach to diffusion models for Text-to-Image synthesis, dubbed AI-T2I. Technically, to address the scattering issue, we devise an aggregation loss to identify and consolidate the scattered intra-token activations, which implicitly helps mitigate the potential overlap issue. Upon that, an isolation loss is further introduced to push the inter-token activations apart, thus fulfilling precise text-to-image alignment. Extensive experiments on various benchmarks demonstrate the superiority of AI-T2I over the state-of-the-art works for text-to-image synthesis. Furthermore, our AI-T2I exhibits excellent generalization across other tasks, e.g., controllable layout generation and personalized generation. Our code is available at https://github.com/Hatter77/AI-T2I.

Shipeng Cao, Biao Qian, Haipeng Liu +2

Key Laboratory of Knowledge Engineering With Big Data, Ministry of Education, Hefei University of Technology, China · Department of Automation, Tsinghua University, China

Diffusion Model Alignment Cross-Attention Attention Control in Diffusion Models Compositional T2I Generation T2I Diffusion Models

May 25, 2026cs.CV

Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences

Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through part-specific modules or localized loss weighting during supervised fine-tuning on high-quality human photos, but such datasets are limited and often provide ambiguous optimization signals due to confounding factors such as lighting, pose, and background. Preference-based alignment offers an alternative, but standard Direct Preference Optimization (DPO) treats all pixels equally and therefore fails to exploit the localized nature of anatomical artifacts. To address this, we propose the framework of Alignment via Synthetic Anatomical Preference (ASAP), which constructs controlled preference pairs through a localized degradation mechanism applied to high-fidelity human images. This mechanism performs a controlled experiment on images by introducing explicit anatomical errors in targeted regions while preserving the remaining content. With this mechanism, we create the Human Anatomical Preference (HAP) dataset with over 10K curated pairs for effective anatomical alignment of text-to-image human image generative models. To better leverage the locality of these controlled preference pairs, we introduce a localized and margin-bounded variant of DPO that prioritizes optimization in targeted anatomical regions while enforcing a finite preference margin to prevent over-optimization and preserve global semantics. We further introduce HAF-Bench, a benchmark for systematic evaluation of anatomical fidelity. Extensive experiments demonstrate that ASAP consistently reduces anatomical errors across multiple foundation models while maintaining overall image quality.

Bao Li, Yuliang Xiu, Zhen Liu

Westlake University · The Chinese University of Hong Kong, Shenzhen

Diffusion Model Alignment Direct Preference Optimization Image Generation T2I Diffusion Models

May 25, 2026cs.CV

DRM: Diffusion-based Reward Model With Step-wise Guidance

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual qualities-such as aesthetics, composition, and visual harmony. In this work, we argue that a model capable of high-fidelity generation must possess a profound understanding of these visual attributes. Based on this insight, we introduce the Diffusion-based Reward Model (DRM), a novel paradigm that use the pre-trained diffusion model as a powerful evaluative backbone. A key advantage of the DRM is its unique ability to assess not only the final image but also the noisy intermediate latents at any stage of the generative process. We leverage this step-wise evaluative capacity in two ways. First, we propose Step-wise GRPO, a reinforcement learning algorithm that provides dense, per-step rewards to resolve the imprecise credit assignment problem in GRPO algorithm, leading to more stable and effective alignment. Second, we introduce Step-wise Sampling, a novel inference strategy that employs the DRM as a dynamic guide to evaluate multiple generation paths at each step, steering the process towards higher-quality outcomes. Extensive experiments confirm that our approach significantly enhances the final quality of generated images. Code: https://github.com/jjaxonx/DRM.

Jaxon Zhang, Binxin Yang, Hubery Yin +2

Peking University · Work done during an internship at WeChat Vision, Tencent Inc. · WeChat Vision, Tencent Inc.

Diffusion Model Alignment Diffusion Model Guidance RL for Diffusion Models T2I Diffusion Models

May 24, 2026cs.LG

Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo

We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its weights. Recent Sequential Monte Carlo (SMC)-based steering methods approximate reward-tilted target distributions in a principled way, but their proposals remain largely tied to the base sampler. Since reward information is mainly used after propagation through particle reweighting and resampling, these methods can require large particle budgets and suffer from weight degeneracy and high-variance estimates. One way to reduce variance and improve particle efficiency is to iteratively learn twisting functions that provide look-ahead guidance, as in twisted SMC. However, existing learnable twisting methods are developed mainly for classical sequential inference and can be unstable when applied to diffusion-based alignment with high-dimensional state spaces and terminal, noisy, or black-box rewards. We propose Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC), a trust-region framework for learning twisting functions in SMC-based inference-time alignment. Each iteration computes an exact KL-constrained update in path space, which admits a closed-form solution by tempered importance reweighting, and projects this target back to the parameterized twisted family by weighted maximum likelihood. Theoretically, we formalize the value-function interpretation of the optimal twisting function and show that it yields a zero-variance sampler. We prove that the trust-region update follows an escort path toward the target distribution, that the weighted maximum-likelihood update is a forward-KL projection, and that the path reduces residual importance-weight variance. Empirically, TRI-TSMC improves primary alignment objectives on discrete diffusion text generation and text-to-image generation under matched inference-time budgets.

Weixin Wang, Yu Yang, Wei Deng +1

Duke University · Morgan Stanley

Diffusion Model Alignment Inference-Time Optimization Diffusion Language Models

May 22, 2026cs.LG

Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy, and its design can significantly affect the reward optimization performance. We break down the sampler design into two interdependent components: choosing the right amount of stochastic exploration, and discretizing the resulting SDE faithfully at the small step counts used in RL. To address the first component, we analyze the inherent tension between exploration and stability in denoising and derive an SDE schedule that balances the two. Turning to the discretization challenge, we use a toy example to show that existing samplers can deviate from the flow-matching process, either by introducing excessive discretization noise or by relying on heuristic rules that do not guarantee convergence to the data distribution. To address these issues, we propose Precise, a new stochastic sampler that balances effective exploration with stability. Crucially, Precise keeps the denoising trajectory SDE-consistent through a novel approximation that freezes the clean-latent posterior mean, resolving the excess noise issue in standard samplers. Extensive experiments demonstrate that this formulation leads to significantly faster and more stable reward optimization via reinforcement learning, achieving state-of-the-art alignment scores (e.g., PickScore, HPSv2.1) while requiring 13.1-53.2% less wall-clock training time to match the best in-domain performance of prior samplers.

Jade Zou, Tao Huang, Weijie Kong +7

Peking University · Tencent Hunyuan

Diffusion Model Alignment Flow Matching Stochastic Differential Equations Diffusion Sampling RL for Generative Models

May 21, 2026cs.SD

Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators

Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline models. However, SOTA models exist in the discrete-AR regime, requiring industrial levels of compute for both training and inference. In this work, we investigate whether audio diffusion models, with their wide support in the open-source community but non-streaming bidirectional nature, can be repurposed efficiently into interactive models accessible on consumer hardware. By taking a critical look at the modern pipeline for block-wise outpainting diffusion, we identify critical inefficiencies during inference that result in strictly worse computational efficiency than their discrete-AR counterparts. We propose Live Music Diffusion Models (LMDMs), a simple modification of the generative diffusion process that recovers, and then outperforms, the inference complexity of the discrete Live Music Models (LMMs) through block-wise KV Caching. Unlike LMMs, LMDMs further enable stable post-training alignment through our novel ARC-Forcing paradigm, reducing error accumulation without any explicit RL or reward models. We demonstrate the application of LMDMs in a number of creative domains, including text-conditioned generation, sketch-based music synthesis, and jamming. We finally show how LMDMs can be used as a generative instrument in a real artist-AI collaboration, utilizing LMDMs as a "generative delay" to transform musicians' improvisation live for variable timbral effects while running locally on a consumer gaming laptop.

Zachary Novack, Stephen Brade, Haven Kim +8

UC San Diego · MIT · Adobe

Diffusion Model Alignment Controllable Music Generation Audio Diffusion Models Diffusion Model Fine-Tuning Diffusion Model Caching Music Generation

May 20, 2026cs.CV

Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models

Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are confined to denoising diffusion models while overlooking flow-matching, and suffer from an objective mismatch when applying discrete NLP-based DPO to regression-based generative tasks.\ In this paper, we derive a generalized DPO objective that covers both diffusion and flow-matching via a unified reverse-time SDE framework, and point out from a gradient perspective that the standard DPO objective is suboptimal for text-to-image generation. Consequently, we propose Linear-DPO, which replaces the aggressive sigmoid-based utility function with a sustained linear utility and incorporates an EMA-updated reference model. Qualitative and quantitative experiments on diffusion models (SD1.5, SDXL) and flow-matching model (SD3-Medium) demonstrate the superiority of our approach over existing baselines.

Kesong Li, Yixuan Xu, Kuo-kun Tseng +3

School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China · Alibaba Group, Hangzhou, Zhejiang, China

Diffusion Model Alignment Flow Matching Direct Preference Optimization T2I Generation

May 20, 2026cs.CV

Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis

Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs). While recent representation alignment methods have proven effective by distilling visual priors from foundation models (e.g., SAM or DINO) into generative latent features, scaling these approaches to pre-trained LDMs at extreme resolutions exposes a critical learnability-fidelity conflict. Specifically, forcing direct patch-wise feature distillation inherently perturbs the pre-trained latent manifold, ultimately leading to generation degradation. To address this bottleneck, we propose Spatial Gram Alignment (SGA), a novel framework that explicitly leverages the representation priors of vision foundation models while preserving the native generative capacity of LDMs. Moving beyond restrictive direct alignment, SGA imposes a non-invasive spatial constraint by aligning the internal self-similarities of the generative features with those of the foundation priors. This spatial constraint effectively establishes macroscopic structural coherence, while the native generative objectives retain the microscopic pixel-level fidelity inherent to the original LDMs. Notably, this versatile strategy integrates seamlessly across both intermediate diffusion features and VAE latents within pre-trained LDMs. Extensive experiments demonstrate that SGA achieves state-of-the-art performance for ultra-high-resolution text-to-image synthesis, yielding an effective reconciliation between global structural integrity and fine-grained visual details. Code is available at https://github.com/zhang0jhon/SGA.

Jinjin Zhang, Xiefan Guo, Di Huang

Beihang University

Diffusion Model Alignment Latent Diffusion Models T2I Diffusion Models

May 20, 2026cs.CV

Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics

Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method for enhancing the photorealism of image generation. However, it often leads to overfitting to the training dataset, corrupts pre-trained image priors, and degrades alignment or aesthetics. To break this bottleneck, we propose a feature supervision paradigm for Multimodal Diffusion Transformers (MM-DiT). Specifically, we introduce a lightweight cross-modal alignment mechanism that implicitly extracts multi-granularity vision-aligned text representations from SigLIP 2 and applies supervision to the image branch of MM-DiT during the training stage, with zero extra inference overhead. Our method injects vision-aligned text guidance while preserving the base model's original generalization, avoiding degradation caused by SFT. Furthermore, our method directly mines implicit multi-granularity aesthetic signals from pre-trained vision foundation models to optimize human-perceived aesthetics. Extensive experiments on MM-DiTs show that our method pushes the Pareto frontier and achieves synergistic improvements across text-image alignment, photorealism, and human-perceived aesthetics.

Yunlong Wang, Jinjin Shi, Wenbin Gao +3

Xiaomi Corporation Nanjing, China · Xiaomi Corporation Beijing, China

Diffusion Model Alignment Diffusion Transformer Image Generation Vision-Language Alignment T2I Diffusion Models

May 19, 2026cs.CV

When Preference Labels Fall Short: Aligning Diffusion Models from Real Data

Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existing approaches rely on preference pairs constructed from model-generated images. Such supervision is inherently relative and can be ambiguous when both samples exhibit artifacts or limited visual quality, making it difficult to infer what constitutes a truly desirable output. In this work, we investigate whether real data can serve as an alternative source of supervision for preference alignment. We adopt a data-centric perspective and study a curation strategy that treats real images as reference points and constructs preference signals by contrasting them with generated or perturbed samples, without requiring manually annotated preference pairs. Through empirical analysis, we show that real-data-based supervision provides effective guidance for aligning diffusion models and achieves performance comparable to existing preference-based methods. Our results suggest that real data offers a practical and complementary source of supervision for preference alignment and highlight directions of label-efficient alignment strategies. Code and models are available at https://cwyxx.github.io/RealAlign.

Weiyan Chen, Weijian Deng, Yao Xiao +5

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Australian National University, Canberra, Australia +2

Diffusion Model Alignment Preference Alignment Diffusion Models

May 19, 2026cs.CV

Stitched Value Model for Diffusion Alignment

For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challenging because the reward is defined for clean output images, but the alignment procedure requires value function estimates at noisy intermediate latents. Existing methods resort to Tweedie-style or Monte Carlo approximations, trading off estimator bias against computational cost: Tweedie estimates are efficient but biased, while Monte Carlo estimates are more accurate but require expensive rollouts. A natural alternative would be a learned value function, but it remains an open question how to effectively train a strong and general value model specifically for noisy latents. Here, we propose StitchVM, a model stitching framework that efficiently transfers reward models pretrained for clean images to the noisy latent regime. StitchVM starts from an existing, truncated pixel-space reward model and attaches a frozen diffusion backbone to it as its head. From the pixel-space model, the resulting hybrid retains a carefully pretrained, robust reward capability; from the diffusion backbone, it inherits its native ability to handle noisy latents. The stitching procedure is exceptionally lightweight, e.g., stitching and finetuning CLIP ViT-L and SD 3.5 Medium takes only 10 GPU-hours. By lifting powerful pixel-space reward models to latent space, StitchVM opens up a new style of diffusion alignment: instead of rough, yet costly per-sample approximation of the value function, the correct function for the actual, noisy latents is constructed once and then amortized over many samples and iterations. We show that this approach yields improvements across a broad range of downstream steering and post-training methods: DPS becomes

3.2\times

faster while halving peak GPU memory, and DiffusionNFT becomes

2.3\times

faster.

Hyojun Go, Hyungjin Chung, Prune Truong +8

1ETH Zurich · 2Google · University of Copenhagen

Diffusion Model Alignment Diffusion Model Guidance RL for Diffusion Models

May 19, 2026cs.CV

Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection

Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds often yield large variations in image quality and prompt-image alignment. We revisit this "seed effect" and show that attention dynamics over prompt core tokens, the content-bearing words, measured during the first few denoising steps, strongly predict final generation quality. Building on this observation, we introduce Attention-Based Seed Selection (ABSS), a training-free, plug-and-play method that ranks seeds for a given prompt by leveraging cross-attention to core tokens during the denoising process. ABSS requires no finetuning and does not alter the initial noise; it scores and ranks all candidate seeds, keeps only the top-k for full generation, and discards the rest, without relying on a fixed accept/reject threshold. Operating purely at inference time, ABSS can serve as a lightweight pre-selection add-on for existing seed-optimization pipelines, enabling additional gains. Across three benchmarks, extensive experiments show that ABSS enables consistent improvements in text-image alignment and visual quality for Stable Diffusion variants, as corroborated by human preference and alignment metrics.

Yunzhe Zhang, Hongfu Liu, Pengyu Hong

Brandeis University

Diffusion Model Alignment T2I Generation T2I Diffusion Models Diffusion Models

May 18, 2026cs.CV

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score (DRS), which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy (DRP), an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone (Z-Image), DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step.

Junyi Wu, Weijian Luo, Haoyang Zheng +2

Purdue University · hi-lab, Xiaohongshu Inc.

Diffusion Model Alignment One-Step Generative Modeling RL for Diffusion Models T2I Diffusion Models

May 18, 2026cs.CV

SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training

Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired with safe-image groundtruth or negative/positive image pairs, making them impractical to scale. Furthermore, offline reinforcement learning and supervised fine-tuning approaches that generate synthetic data offline suffer from catastrophic forgetting, degrading generation quality. We propose a novel online reinforcement learning framework that addresses both data scarcity and model degradation through post-training with Group Relative Policy Optimization (GRPO) on both negative and positive text prompts. To eliminate the need for fine-tuning specialized safe/unsafe reward models, we introduce a \textit{steering reward mechanism} that exploits an inherent property of CLIP embeddings: steering text representations toward positive safety directions and away from negative ones in the embedding space. Our online-policy approach enables the model to learn from diverse prompts, including explicit unsafe content, without catastrophic forgetting. Extensive experiments demonstrate that our method reduces inappropriate content to 18.07% (vs. 48.9% for SD v1.4) and nudity detections to 15 (vs. 646 baseline) while improving compositional generation quality from 42.08% to 47.83% on GenEval. Remarkably, these safety gains generalize to out-of-domain unsafe prompts across seven harm categories, achieving state-of-the-art performance without supervised paired data or reward tuning. Github: https://github.com/MAXNORM8650/SafeDiffusion-R1.

Komal Kumar, Ankan Deria, Abhishek Basu +3

Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE · Michigan State University (MSU), USA

Diffusion Model Alignment Diffusion Model Fine-Tuning RL for Diffusion Models T2I Diffusion Models Diffusion Models

May 16, 2026cs.AI

TILT: Model-Intrinsic Reward Alignment For Compositional Diffusion

Consider conditional generation

p(x \mid C=\{c_1, c_2, \dots c_k\})

where

C

is a prompt composed of multiple concepts

c_i

. Diffusion models often struggle with compositional prompts, producing samples in which some concepts dominate while others are missing or weakly represented. Prior work attributes these failures to mode collision, where single-concept modes of

p(x\mid c_i)

overlap with modes of the joint

p(x \mid C)

. To seek out collision-free modes of

p(x \mid C)

, or "pure modes", corrector-based approaches have attempted to suppress collisions at intermediate diffusion times. However, local corrections are often heuristic and do not necessarily steer the generation to a "pure mode" in the final data space. Derived from a principled formulation, we present TILT (Test-time model-Intrinsic reward aLignment via Tilting), a training-free framework that poses eventual pure mode sampling as a reward for intermediate-time alignment. This reward offers valuable advantages: (1) it is intrinsic to the model, hence external reward models need not be trained by modality-specific datasets, (2) it yields a closed-form target under a variational approximation, which makes it realizable through standard diffusion sampling, and (3) it is interpretable, hence amenable to preference-based modifications. Project page: https://debottam-dutta7.github.io/tilt_web/

Debottam Dutta, Jianchong Chen, Jaehoon Hahm +1

Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA · Zhejiang University, China · Physics, University of Illinois Urbana-Champaign, Urbana, IL, USA

Diffusion Model Alignment Diffusion Model Guidance Diffusion Guidance Diffusion Sampling Compositional Image Generation

May 16, 2026cs.CV

Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers

Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-can substantially accelerate training and improve generation fidelity. Subsequent analysis(e.g., iREPA) suggests that these gains arise primarily from transferring spatial structure contained in pre-trained vision representations. However, mostly existing alignment methods employ point-wise matching objectives or rely on implicit architectural tweaks, which fail to explicitly model the spatial relational geometry inherent in vision foundation models. We argue that such element-wise supervision is insufficient to capture the rich spatial topology of visual representations, and that effective alignment for generation should instead be formulated as an explicit structural constraint. To this end, we propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps, rather than merely matching individual feature points. By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence, along with improved sample quality, compared to state-of-the-art alignment strategies. Our code and models will be released.

Shaodong Xu, Zhendong Wang, Litong Gong +4

University of Science and Technology of China

Diffusion Model Alignment Diffusion Transformer Diffusion Model Acceleration Representation Alignment

May 15, 2026cs.CV

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

Xiaoxuan He, Siming Fu, Zeyue Xue +9

Zhejiang University · Joy Future Academy · Independent Researcher +1

Diffusion Model Alignment Video Diffusion Models Group Relative Policy Optimization Diffusion Policy RL for Diffusion Models Diffusion Model Acceleration

May 15, 2026cs.CV

Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?

Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards. However, most studies apply RL to the full denoising trajectory, making it computationally costly and weakening preference alignment, i.e., doing more but achieving less. We observe that the impact of RL fine-tuning varies significantly across denoising stages. In the early stage, image structures are unstable and distant from the final reward signal. Applying RL at this stage leads to delayed rewards and action-reward mismatching, resulting in high variance and inefficient updates. Conversely, in the later stage, reward gains saturate, and continued training tends to overfit local details, intensifying reward hacking. To tackle these challenges, we propose AdaScope, an RL-enhanced plug-in that improves generation quality while reducing computational cost. Specifically, AdaScope adaptively identifies the optimal intervention timing for RL by perceiving the structural evolution and semantic consistency during denoising, and dynamically terminates training once the denoising converges and reward gains saturate. As a result, it achieves a rare 'dual benefit': a reduction in computational costs alongside a significant performance improvement. We offer theoretical grounds for the design of AdaScope. Compared with state-of-the-art methods, AdaScope improves performance by 66% while cutting computational cost by 59%.

Renye Yan, Jikang Cheng, Shikun Sun +7

1Peking University · 2Tsinghua University · 3Nanjing University +1

Diffusion Model Alignment Diffusion Sampling Diffusion Model Fine-Tuning RL for Diffusion Models

May 14, 2026cs.CV

LPH-VTON: Resolving the Structure-Texture Dilemma of Virtual Try-On via Latent Process Handover

Virtual Try-On (VTON) aims to synthesize photorealistic images of garments precisely aligned with a person's body and pose. Current diffusion-based methods, however, face a fundamental trade-off between structural integrity and textural fidelity. In this paper, we formalize this challenge as a consequence of complementary inductive biases inherent in prevailing architectures: models heavily reliant on spatial constraints naturally favor geometric alignment but often suppress textures, whereas models dominated by unconstrained generative priors excel at vibrant detail rendering but are prone to structural drift. Based on this diagnosis, we propose LPH-VTON, a new synergistic framework that resolves this tension within a single, continuous denoising process. LPH-VTON strategically decomposes the generation, leveraging a structure-biased model to establish a geometrically consistent latent scaffold in the early stages, before handing over control to a texture-biased model for high-fidelity detail rendering. Extensive experiments validate our approach. Our model achieves a superior Pareto-optimal balance, establishing new benchmarks in perceptual faithfulness while maintaining highly competitive structural alignment across the standard dataset VITON-HD, proving the efficacy of temporal architectural decoupling.

Yixin Liu, Baihong Qian, Jinglin Jiang +6

Shanghai Jiao Tong University

Diffusion Model Alignment Virtual Try-On Diffusion-Based Image Generation

May 13, 2026cs.CV

Pareto-Guided Optimal Transport for Multi-Reward Alignment

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on weighted summation, which is costly to tune and insufficient for balancing conflicting objectives. More critically, optimization with reward models is highly susceptible to reward hacking, where reward scores increase while the perceived quality of generated images deteriorates. We demonstrate that optimizing against a unified global target under heterogeneous reward upper bounds can induce reward hacking, a risk further exacerbated by the inherent instability of weak reward models. To mitigate this, we propose a Pareto Frontier-Guided Optimal Transport (PG-OT) framework. Our method constructs a prompt-specific Pareto frontier and maps dominated samples toward it via distribution-aware optimal transport. Furthermore, we develop both online and offline optimization strategies tailored to diverse reward signal characteristics. To provide a more rigorous assessment, we introduce the Joint Domination Rate (JDR) and Joint Collapse Rate (JCR) as principled metrics to quantify multi-reward synergy and reward hacking. Experimental results show that our approach outperforms strong baselines with an 11% gain in JDR and achieves a near 80% win rate in human evaluations.

Ying Ba, Tianyu Zhang, Mohan Zhou +5

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE 4Tomorrow Advancing Life +2

Diffusion Model Alignment Reward Hacking Multi-Objective Language Model Alignment T2I Diffusion Models Optimal Transport

May 12, 2026cs.CV

CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis

Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible synthesis, while existing metrics such as FID or Inception Score do not quantify per-image alignment with pathology-relevant criteria. We introduce the Clinical Alignment Score (CAS), a foundation-model-based proxy for clinical alignment that evaluates generated images along four complementary dimensions beyond visual fidelity. Building on CAS, we propose Clinical Reward-Aligned Finetuning (CRAFT), a reward-based adaptation framework that transfers medical knowledge from multimodal large language models and vision-language models through label-conditioned prompt enrichment, clinical checklists, and differentiable reward optimization. Across four diverse modalities, CRAFT improves CAS and downstream classification performance over strong adaptation baselines. Beyond average CAS gains, CRAFT reduces the empirical low-alignment tail below a real-image reference threshold by 5.5-34.7% points relative to the strongest baseline, corresponding to a 20.4% average relative reduction across datasets. These results indicate fewer hallucination-like generations under CAS, and are corroborated by out-of-family evaluator evaluation, structured checklist auditing, memorization analysis, and a blinded physician preference study on CheXpert.

Yunsung Chung, Alex El Darzi, Carlo El Khoury +3

Department of Computer Science, Tulane University, New Orleans, LA 70118 · School of Medicine, Tulane University, New Orleans, LA 70112

Diffusion Model Alignment Healthcare Medical Image Analysis Diffusion Model Fine-Tuning Medical Image Synthesis

May 12, 2026cs.LG

Efficient Adjoint Matching for Fine-tuning Diffusion Models

Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a principled formulation by casting reward fine-tuning as a stochastic optimal control (SOC) problem. However, AM inevitably requires a substantial computational cost: it requires (i) stochastic simulation of full generative trajectories under memoryless dynamics, resulting in a large number of function evaluations, and (ii) backward ODE simulation of the adjoint state along each sampled trajectory. In this work, we observe that both bottlenecks are closely tied to the \textit{non-trivial base drift} inherited from the pretrained model. Motivated by this observation, we propose \textbf{Efficient Adjoint Matching (EAM)}, which substantially improves training efficiency by reformulating the SOC problem with a \textit{linear base drift} and a correspondingly modified \textit{terminal cost}. This reformulation removes both sources of inefficiency; it enables training-time sampling with a few-step deterministic ODE solver and yields a closed-form adjoint solution that eliminates backward adjoint simulation. On standard text-to-image reward fine-tuning benchmarks, EAM converges up to 4x faster than AM and matches or surpasses it across various metrics including PickScore, ImageReward, HPSv2.1, CLIPScore and Aesthetics.

Jeongwoo Shin, Dongsoo Shin, Yuchen Zhu +5

Seoul National University · Georgia Institute of Technology · Sungkyunkwan University

Diffusion Model Alignment Stochastic Optimal Control Diffusion Model Fine-Tuning RL for Diffusion Models T2I Diffusion Models

May 12, 2026cs.LG

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives

Inference-time reward alignment asks how to turn a pre-trained diffusion model with base law

p

into a sampler that favors a reward

r

while remaining close to

p

. Since there is no canonical distributional distance for this closeness constraint, different choices lead to different "reward-aligned" laws and, just as importantly, different algorithmic problems. We develop a primitive-based approach to reward alignment: rather than assuming arbitrary reward-aligned laws can be sampled, we ask which simple algorithmic primitives suffice to implement alignment for non-trivial reward classes. If closeness is measured in KL distance, the target law is

q(x) \propto p(x) \exp(λ^{-1}r(x))

. For this setting, we show that linear exponential tilts of the form

q(x)\propto p(x)\exp(\langle θ, x \rangle)

-- which according to recent work [MRR26] can be efficiently sampled from -- are a sufficient primitive for aligning to a very broad class of convex low-dimensional rewards. If closeness is measured in Wasserstein distance, the corresponding primitive is a proximal transport oracle: given

x

, solve

\mbox{argmax}_y \{r(y)- λc(x,y)\}

. This oracle can be efficiently implemented for concave or low-dimensional Lipschitz rewards

r(x)=f(Ax)

. Together, these results illustrate that the choice of distribution distance for alignment affects the computational primitive and the tractable reward class.

Ankur Moitra, Andrej Risteski, Dhruv Rohatgi

Diffusion Model Alignment KL-Regularized RL

May 12, 2026cs.LG

Gradient-Free Noise Optimization for Reward Alignment in Generative Models

Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to deterministic generators. A natural alternative is noise-space optimization, but existing approaches require backpropagation through the generator and reward pipeline, limiting applicability to differentiable settings. To address this, here we present ZeNO (Zeroth-order Noise Optimization), a gradient-free framework that formulates noise optimization as a path-integral control problem, estimable from zeroth-order reward evaluations alone. When instantiated with an Ornstein--Uhlenbeck reference process, the update connects to Langevin dynamics implicitly targeting a reward-tilted distribution. ZeNO enables effective inference-time scaling and demonstrates strong performance across diverse generators and reward functions, including a protein structure generation task where backpropagation is infeasible.

Jeongsol Kim, Hongeun Kim, Jian Wang +1

KAIST AI1 · Snap Inc.2

Diffusion Model Alignment Stochastic Optimal Control Zeroth-Order Optimization Generative Modeling Derivative-Free Optimization

May 11, 2026cs.LG

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image generation, this makes samples compose objects correctly, render text legibly, and match human preferences. Existing methods rely on costly SDE rollouts, reward gradients, or surrogate losses, sacrificing pretraining's regression structure. We show that the structure extends to RL post-training. Under KL-regularized reward maximization, the optimal generative process tilts the clean-endpoint distribution towards samples with higher reward and leaves the noising law unchanged. Combining this with the adjoint-matching optimality condition and a REINFORCE identity, we derive Reinforce Adjoint Matching (RAM): a consistency loss that corrects the pretraining target with the reward. At each step, we draw a clean endpoint from the current model, evaluate its reward, noise it as in pretraining, and regress. No SDE rollouts, backward adjoint sweeps, or reward gradients are required. Like the pretraining objective, RAM is simple and scales. On Stable Diffusion 3.5M, RAM achieves the highest reward on composability, text rendering, and human preference, reaching Flow-GRPO's peak reward in up to

50\times

fewer training steps.

Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2

1TU Munich, MCML · 2MIT CSAIL · 3King’s College London +2

Diffusion Model Alignment Flow Matching RL for Diffusion Models RL for Generative Models RL Post-Training

May 10, 2026cs.CV

Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study

Voxel-wise dose prediction is a critical yet challenging task in practical radiotherapy (RT) planning, as bespoke models trained from scratch often struggle to generalize across diverse clinical settings. Meanwhile, generative models trained on billion-scale datasets from vision domains have achieved impressive performance. Herein, we propose DiffKT3D, a unified Any2Any 3D diffusion framework that leverages prior knowledge from pretrained video diffusion models for efficient and clinically meaningful dose prediction. To enable flexible conditioning across multiple clinical modalities (CT, anatomical structures, body, beam settings, etc.), we introduce an Any2Any conditional paradigm utilizing modality-specific embeddings without cross-attention overhead. Further, we design a novel reinforcement learning (RL) post-training mechanism guided by a clinically-informed Scorecard explicitly tailored to institutional treatment preferences. Compared with winner of GDP-HMM challenge, DiffKT3D sets a new state-of-the-art in dose prediction by reducing voxel-level MAE from 2.07 to 1.93. In addition, DiffKT3D achieves superior image quality and preference match. These results demonstrate that transferring diffusion priors via modality-aware conditioning and clinically aligned RL post-training can provide a robust and generalizable solution for RT planning across various clinical scenarios.

Yuhan Wang, Zihan Li, Han Liu +7

1UC Santa Cruz · 2Siemens Healthineers · University of Washington

Diffusion Model Alignment Conditional Diffusion Models

May 9, 2026cs.LG

TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing visual mode collapse and amplifying unreliable rewards. We identify the root cause as the mode-seeking nature of these methods, which maximize expected reward without effectively constraining probability distribution over acceptable trajectories, causing concentration on a few high-reward paths. In contrast, we propose Trajectory Matching Policy Optimization (TMPO), which replaces scalar reward maximization with trajectory-level reward distribution matching. Specifically, TMPO introduces a Softmax Trajectory Balance (Softmax-TB) objective to match the policy probabilities of K trajectories to a reward-induced Boltzmann distribution. We prove that this objective inherits the mode-covering property of forward KL divergence, preserving coverage over all acceptable trajectories while optimizing reward. To further reduce multi-trajectory training time on large-scale flow-matching models, TMPO incorporates Dynamic Stochastic Tree Sampling, where trajectories share denoising prefixes and branch at dynamically scheduled steps, reducing redundant computation while improving training effectiveness. Extensive results across diverse alignment tasks such as human preference, compositional generation and text rendering show that TMPO improves generative diversity over state-of-the-art methods by 9.1%, and achieves competitive performance in all downstream and efficiency metrics, attaining the optimal trade-off between reward and diversity.

Jiaming Li, Chenyu Zhu, Nanxi Yi +9

1MAIR Lab, Huazhong University of Science and Technology · 2Kuaishou Technology · 3Nanyang Technological University +2

Diffusion Model Alignment Reward Hacking RL for Diffusion Models Mode Collapse