RL for Diffusion Models

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 467% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 120

Oct 5, 2026cs.LG

Reachability-Aware Diffusion Policy Optimization

Diffusion policies provide expressive action distributions for continuous-control reinforcement learning. However, safety-aware online diffusion policy optimization remains underexplored, particularly methods that use predictive reachability information without an explicit dynamics model. We propose Reachability-Aware Diffusion Policy Optimization (RADPO), a model-free method that combines predictive first-hit safety estimation with cumulative-cost budget feedback. RADPO learns a discounted first-hit reachability value that captures the discounted risk of a cost event, assigns larger weight to events that occur sooner, and uses this signal to shape the reward. A separate dual-like multiplier adjusts the shaping strength according to realized episodic costs relative to a prescribed budget. The diffusion actor improves through weighted denoising regression on candidate actions scored by the reward critic. Our approach requires neither a learned dynamics model, action gradients through the critics, nor differentiation through the reverse diffusion sampler. We establish theoretical properties of the reachability value and show that accumulated reachability penalty provides a conservative surrogate for future discounted cumulative cost. Across ten continuous-control safety tasks, RADPO achieves competitive reward-cost trade-offs, with substantial reductions in constraint violations on several tasks relative to the compared baselines. Our theoretical and empirical analysis supports that combining reachability with cumulative budget feedback is a viable approach to safety-aware diffusion policies.

Hikmet Simsir, Kutay Demiray, Ozgur S. Oguz

Department of Computer Engineering, Bilkent University

Constrained RL Diffusion Policy RL for Diffusion Models Model-Free RL Safe RL

Oct 4, 2026cs.CV

MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation

Diffusion-based dataset distillation (DD) suffers from a fundamental objective mismatch: likelihood-driven diffusion models prioritize density approximation over the discriminative decision boundaries required for downstream tasks. Beyond semantic mismatch, relying solely on density also leads to geometric coverage loss, where generated samples collapse into a few high-density modes and fail to cover the manifold's structural diversity. We propose Manifold-Guided Policy Optimization (MGPO), which reformulates DD as a multi-objective reinforcement learning problem and achieves Dual-Space Alignment via a pixel-space discriminative reward and a latent-space geometric reward guided by a class-wise Minimum Spanning Tree (MST). The discriminative reward enforces class separability, while the MST-based geometric reward encourages generated latents to cover a sparse geometric skeleton of each class, jointly addressing both failure modes. We further provide an idealized analysis that motivates the MST-based reward, including a Hausdorff approximation bound and a subsampling bound independent of the dataset size. The reward-modular design extends to structured tasks such as object detection and segmentation by substituting the frozen task reward model. Extensive experiments show MGPO consistently outperforms existing methods, including a +8.0% mIoU gain on segmentation under low-budget settings.

Yunyi Chen, Chenru Wang, Xinyi Ye +2

AGI Lab, Westlake University · Eindhoven University of Technology · Guangdong University of Finance and Economics

Diffusion Model Alignment Dataset Distillation RL for Diffusion Models

Oct 1, 2026cs.CV

Token-Level Video Reinforcement Learning

Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: some visual tokens may already satisfy the prompt, whereas others require correction. A scalar reward cannot localize errors, causing optimization to perturb satisfactory tokens while under-targeting the tokens that actually need to change. We introduce Token-Level Video Reinforcement Learning, TVRL, a framework that derives token-level credit from the reward being optimized. Our key insight is that the answer likelihood of a frozen vision-language model provides both signals: its outputs contribute to the video-level reward, while magnitudes of its video-input gradients reveal which generated video tokens most affect that score. We instantiate TVRL in Group Relative Policy Optimization by averaging prompt-derived question rewards into one group-relative advantage and using detached, question-conditioned token-credit maps to reweight dense denoising-transition log-probabilities inside the clipped policy ratio. On VBench-2.0, TVRL achieves an Overall score of 57.69, outperforming the base model by 3.60 points. TVRL also improves matched GRPO baselines across three SDE samplers (SAGE, Flow, and Dance) by 2.68--3.15 points and across four reward models (VideoAlign, VideoScore2, UnifiedReward2, and Qwen3.5-9B) by 1.33--3.15 points.

Yifan Wang, Gordon Guocheng Qian, Yanyu Li +2

Northeastern University

Video Diffusion Models RL for Video Generation Token-Level Credit Assignment RL for Diffusion Models

Oct 1, 2026cs.LG

iADD: Improving Alignment and Diversity in Diffusion Policy Optimization

Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a reward function. However, current approaches to reward optimizations do so at the cost of diversity and quality. In this paper, we provide better tradeoffs through careful theoretical considerations and method design. We analyze the theoretical framework and mathematically demonstrate that \emph{only-latter timestep} updates of diffusion model may be harmful for diversity contrary to the conclusions presented in a previous work. Additionally, we propose an incremental Feynman-Kac training based on strong theoretical foundations in order to achieve the best-yet alignment-diversity tradeoffs. We perform extensive experiments and compare our method against related diffusion policy optimization approaches in three different tasks and also provide strong ablations for each component, thus validating strong performance gains in both alignment and diversity.

Ashok Prasad Neupane, Saugat Adhikari, Pramish Paudel +2

Pulchowk Campus, IOE, Tribhuvan University, Lalitpur, Nepal · INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria · NAAMII, Kathmandu, Nepal

Diffusion Model Alignment Generative Modeling RL for Diffusion Models

Sep 30, 2026cs.LG

Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models

Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcement learning with verifiable rewards (RLVR) reuses terminal feedback across these decisions, even as their conditioning context changes. We propose stepwise risk-sensitive GRPO (StepRS-GRPO), which varies the risk coefficient of the group-advantage transformation across denoising states while retaining the underlying trainer. For binary rewards, we show that this transformation is exactly a prompt- and state-dependent rescaling of centered outcome advantages. A capability-based calibration suggests a coefficient scale, while endpoint and interpolation ablations guide schedule selection. Across multiple dLLM backbones and mathematical reasoning benchmarks, StepRS-GRPO improves both pass@1 accuracy and pass@k coverage over centered GRPO, while increasing answer diversity. In our ablation studies, mass-matched controls support the contributions of state allocation and schedule direction, and the gains persist after matching the root mean square (RMS) of the advantages to that of centered GRPO. Reasoning-trace diagnostics further show that the diversity gains from StepRS-GRPO extend beyond final-answer strings.

Yue YU, Bowen Zuo, David Crandall +2

Indiana University · University of California, Riverside

RL for Language Model Reasoning Group Relative Policy Optimization Risk-Sensitive RL RL for Diffusion Models Diffusion Language Models LLM Reasoning

Sep 30, 2026cs.LG

Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models

Masked diffusion language models (dLLMs) have shown strong potential for faster inference through parallel token generation when combined with confidence-based samplers. However, recent work has shown that such methods can defer unmasking high-entropy fork positions at which multiple plausible continuations exist. This results in reduced generation diversity, as shown by worse pass@k scaling, and limits gains obtainable from RL post-training. To avoid this flexibility trap, prior work advocated for autoregressive (AR) sampling. Here, we show that discarding confidence-based sampling is unnecessary and, once inference cost is taken into account, wasteful. We first propose Fork-dLLM, a simple hybrid sampler that uses AR-style ordering only at uncertain fallback steps while retaining parallel generation otherwise. We then extend the same principle to post-training with ForkGRPO, which uses Fork-dLLM rollouts and applies the GRPO objective only at fallback steps, preserving exact policy-likelihood ratios while substantially reducing rollout and optimization cost. In our experiments, Fork-dLLM matches the strong pass@k scaling of AR sampling while being 2-3x more efficient, and ForkGRPO achieves downstream performance comparable to or better than AR-based GRPO baselines at a substantially lower training cost.

Stipe Frković, Metod Jazbec, Christian A. Naesseth

University of Amsterdam · UvA-Bosch Delta Lab, University of Amsterdam

Masked Diffusion Models Speculative Decoding for Diffusion Language Models Diffusion Language Model Decoding RL for Diffusion Models Diffusion Model Inference Acceleration

Sep 30, 2026cs.CV

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

Online reinforcement learning has been extended to flow matching for diffusion model (DM) image generation. However, this paradigm faces three limitations: (1) Window selection. Existing methods manually set the stochastic differential equation (SDE) sampling window, i.e., the denoising steps where exploration noise is injected. We instead determine it from each model's denoising trajectory. (2) Reward saturation. Current methods rely on scoring models trained on human annotations; we find that such scores are extremely high and nearly indistinguishable on the latest SOTA open-source DMs, making advantage estimation largely ineffective. (3) Sample inefficiency. A single scalar reward collapses different failure modes into almost identical scores, leaving minimal gradient guidance for targeted improvement. To address these issues, we propose CAST (Causal Advantage-Structured Training), an RL fine-tuning method for pretrained DMs, which (1) identifies the denoising step at which each model fixes the objects and their spatial arrangement in the image and uses that timing to set the SDE window, (2) decomposes each prompt via Causal Scene Graphs (CSG) into verifiable-atoms, i.e., minimal semantic units such as an object, count, attribute, or spatial relation that can each be checked independently, and rewards each atom separately, and (3) projects the signed atom-level advantages into pixel space through teacher-forced attention and uses them to spatially weight the SDE policy objective. We fine-tune two of the strongest open-source DMs, FLUX.2-dev and Qwen-Image-2512, with CAST, and evaluate them on GenEval 2, a compositional benchmark, and on Qwen-Image-Bench for overall quality. Within almost the same training budget, CAST's improvement over the base model on the most challenging GenEval 2 prompts is up to 3.07x that of Flow-GRPO, while overall generation quality also improves.

Shu Yu, Chaochao Lu

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

Diffusion Model Fine-Tuning Compositional T2I Generation RL for Diffusion Models Flow-Based Generative Modeling Reward Design for RL

Sep 29, 2026cs.CV

ExploreNet: Learning Where to Explore in Diffusion GRPO

Group-relative RL methods such as Flow-GRPO post-train image generators by exploring with isotropic Gaussian noise added at every denoising step. This noise decides which rollouts the model learns from, yet it perturbs every channel and spatial position of the latent equally. In this paper, we instead show that latent elements differ in how much they change the generated image, so exploration should adapt to these differences. We introduce EXPLORENET to learn an adaptive exploration distribution. EXPLORENET is a policy that predicts a noise scale for every latent element from the current latent, the denoising step, and the prompt, before any reward is observed; it is trained on the reward spread of each rollout group and discarded after training, leaving inference unchanged. On Stable Diffusion 3.5 Medium, EXPLORENET improves held-out GenEval2 by 14% over Flow-GRPO, transfers to two independent compositional benchmarks and five preference and image-quality models, and reaches a 67.2% human preference win-rate. Overall, across our group-relative diffusion RL experiments, we find that exploration is learnable, the shape of the exploration distribution outweighs its magnitude, and rollout quality is more effective than rollout quantity.

Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov +1

University of Washington

Diffusion Model Fine-Tuning RL Exploration RL for Image Generation RL for Diffusion Models T2I Diffusion Models

Sep 29, 2026cs.AI

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

MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tuning: existing advantage-based objectives are typically defined on instantaneous velocities or equivalent

x_0

-space predictions, whereas inference directly uses the learned average-velocity map. We introduce MeanFlowAdvantage, a signed advantage-weighted least-squares objective for average-velocity generators. Our key construction uses a shared, detached MeanFlow derivative correction to express the reward objective in prediction space while making rollout and reference regularization exact penalties on the average-velocity network deployed at inference. The resulting formulation preserves MeanFlow's native few-step sampler and provides a direct mechanism for transferring reward improvements to the deployed flow map. On SD3.5-Medium, MeanFlowAdvantage improves all eight reported metrics over the matched four-step MeanFlowNFT baseline and, with only four NFEs, matches or exceeds the 40-step DiffusionNFT baseline on six of eight metrics. The same objective also transfers to DNA promoter design, where it supports both teacher-free on-policy RL for a generator defined on a manifold and teacher-guided reward-graded distillation, with the latter yielding the lowest one-step Sei profile MSE among the compared configurations.

Haocheng Tang, Tianchi Xie, Xingqiao Lin

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

Flow Matching MeanFlow Few-Step Diffusion Sampling Diffusion Model Fine-Tuning Flow Map Learning RL for Diffusion Models+1

Sep 29, 2026cs.CV

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Multi-reward guided reinforcement learning (i.e., RL) offers a promising way to improve joint audio-video diffusion models along several complementary objectives, including modality-specific quality, cross-modal semantic alignment, and temporal synchronization. Its effectiveness, however, depends on two quantities that change during training: where reward-driven updates should act, and how competing rewards should be combined. Existing methods tend to rely on fixed routing and reward weights, failing to track evolving model functions. To address these limitations, we propose Adaptive Reward Routing to jointly adapt update locations and reward coordination during forward-process RL (i.e., DiffusionNFT) of joint audio-video diffusion models. Our method consists of two components. (i) Cross-Modal Influence-Guided Routing (Localizing Updates): We use bidirectional cross-attention responses as an efficient proxy for evolving cross-modal influence, dynamically reweighting token-aware losses and scaling gradients across cross-modal layers without additional model interventions. (ii) Preference-Preserving Modality-Aware Reweighting (Coordinating Rewards): We preserve predefined weights as preference priors and use branch-specific reward-gradient interactions as residual corrections after warm-up. This resolves evolving conflicts without letting dominant rewards suppress weak but essential objectives. Extensive experiments demonstrate consistent improvements in modality quality, semantic consistency, and audio-video synchronization over strong RL baselines. Ablations and mechanism analyses further validate the complementary benefits of adaptive update routing and reward coordination.

Songlin Yang, Xiaotong Zhao, Jiacheng Zhang +5

Tencent Video · The University of Hong Kong

Multi-Objective Reinforcement Learning Cross-Modal Alignment RL for Diffusion Models Multimodal Diffusion Models

Sep 28, 2026cs.CV

Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization

Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. However, reward-maximizing RL causes policy mode collapse even under reference KL or entropy regularization, reducing the policy to a single high-reward mode. In T2I, this produces similar images and reward hacking. When extended to vision-language-action (VLA) models, the same collapse removes alternative successful strategies and weakens task and scene generalization. To address this limitation, we introduce Unified Trajectory Matching Policy Optimization (Uni-TMPO), a unified RL post-training framework for diffusion and flow policies. First, Uni-TMPO converts standardized rewards into a target distribution within each trajectory group and derives the policy distribution from trajectory log probabilities. Then, forward Kullback-Leibler optimization matches the two distributions instead of maximizing expected reward. A progress-conditioned coarse-to-fine scheduler efficiently constructs T2I trajectories. Within the unified framework, feedback-conditioned sampling uses updated observations to construct VLA trajectories. Extensive experiments show that Uni-TMPO achieves higher T2I rewards and VLA ID success rates than the strongest baselines. More importantly, it achieves the best T2I reward-diversity-efficiency trade-off and VLA generalization to held-out tasks and scenes, while real-robot evaluation demonstrates the value of multiple action strategies when the higher-reward target is blocked.

Zhiyuan Ma, Jiaming Li, Lingzhen Li +7

School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China

Reinforcement Learning Vision-Language-Action Models RL for Diffusion Models T2I Diffusion Models

Sep 27, 2026cs.RO

Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies

Generative robot policies provide expressive behavior priors, but updating a large diffusion or flow-matching model through online interaction is costly. Latent-space reinforcement learning avoids updating the pretrained generator by controlling its initial sampling noise, yet high-dimensional noise can have strongly anisotropic effects on decoded actions. We introduce Principal Steering Subspaces (PSS), a forward-query interface that constructs a fixed low-dimensional control basis from finite-difference decoder responses. Soft Actor-Critic controls the leading response directions, while the orthogonal complement is independently resampled from the Gaussian prior at each query. On three RoboMimic tasks with diffusion and flow-matching policies, response spectra reveal substantial concentration. Across five matched task-generator pairs, the training curves indicate that PSS generally converges faster and exhibits more stable late-training behavior than full-latent control, while achieving stronger final performance overall. Controlled Diffusion-Square ablations further show that leading-response directions outperform random and least-responsive subspaces of equal dimension. We further integrate PSS with a frozen, closed-source 3B-parameter vision-language-action (VLA) policy in a humanoid learning system with synchronous transition collection, reset-time optimization, and latency-aware asynchronous deployment. In an exploratory screwdriver-placement evaluation, success is observed in 2/10 trials for the frozen VLA policy and 6/10 after SAC+PSS adaptation. These results support decoder-response geometry as a practical basis for online adaptation of frozen generative robot policies.

Jialeng Ni, Nathan Zhao, Kunpeng Song

University of Michigan, Ann Arbor, MI, USA. · XPENG Robotics, Santa Clara, CA, USA.

Robot Policy Learning Reinforcement Learning Diffusion Policy RL for Diffusion Models

Sep 27, 2026cs.LG

Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning

A nascent family of methods that forgoes the policy gradient and reweights a supervised regression instead has garnered momentum in reinforcement learning for diffusion and flow models. DiffusionNFT, FlowAWR, and RAM are representative regimes with contrasting motivations. It is yet opaque what, if anything, they share. We substantiate that each is the solution of one divergence-constrained reward-maximization problem, and they are differentiated only by the convex generator that defines the constraint. Under the unified modeling framework, we unravel the relaxations that prior art made during building the advantage-embedded regression target: approximating the KKT condition and posterior normalizer for the linear and exponential tilt shapes DiffusionNFT and FlowAWR respectively, while preserving the exact sparsemax projection onto the probability simplex for linear tilt leads to another superior model type in this work. Beyond the theoretical underpinnings, we further empirically investigate the design space and shed light on the training recipe for regression-style diffusion RL. Retaining the merits discovered during our exploration gives rise to DiffusionRFT, our paradigm that converges faster, trains more stably, and attains the top performance.

Toyota Li, David Zhao, Alan Zhao

Tencent

Reinforcement Learning Constrained RL Diffusion Model Fine-Tuning RL for Diffusion Models

Sep 25, 2026cs.LG

DOHF: Online Diffusion Fine-tuning with Doob's $h$ -transform Guidance

Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to estimate. In this work, we propose Diffusion Online

h

-guidance Fine-tuning (DOHF), which turns Doob's

h

-transform into a practical online training algorithm. DOHF assigns optimality weights to generated samples, estimates the normalized local correction

\nabla\log h

under the current rollout policy, and distills it directly into the generative model. Theoretically, we characterize the population-optimal DiffusionNFT update as well as the various classfier free guidance methods through a unified

h

-transform perspective. Methodologically, our framework accommodates black-box and non-differentiable rewards without additional network evaluations. We further show improved alignments under three empirical scenarios. Our work demonstrates how adapting probabilistic conditioning through inexpensive estimation and iterative distillation can improve generative learning across statistical sampling and visual generation.

Zhengyi Guo, Jiayuan Sheng, Wenpin Tang +1

Diffusion Model Alignment Diffusion Model Guidance Doob H-Transform Diffusion Model Fine-Tuning RL for Diffusion Models

Sep 24, 2026cs.CV

AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audio-video generation is challenging. Heterogeneous multimodal rewards entangle learning signals and complicate credit assignment. Joint optimization of two modality towers is computationally expensive given their divergent dynamics. Moreover, synchronization evaluation difficulty depends on paired samples, preventing fair reward comparisons. We propose AV-GRPO, a modality-anchored online diffusion RL framework, and 5DAV, a decoupled, difficulty-controllable training dataset. AV-GRPO includes three key modules: (1) modality-anchored rollouts to disentangle learning signals and stabilize difficulty; (2) trajectory-locked frozen-tower optimization to reduce cost and reassign credit; (3) adaptive objectives and perturbation strengths tailored to modality-specific dynamics. This converts coupled multimodal preference learning into unimodal subproblems for precise reward attribution and better synchronization. Our 5DAV dataset decouples samples across five dimensions for systematic training. Experiments on JavisBench and VABench demonstrate AV-GRPO outperforms LTX-2.3 in generation quality, semantic alignment and cross-modal synchronization under LoRA and full fine-tuning. Ablations confirm our designs. Code and data: https://github.com/zhiyuxu03/AV-GRPO

Zhiyu Xu, Weilong Yan, Yufei Shi +4

Shanghai AI Laboratory · The Hong Kong Polytechnic University · National University of Singapore +2

Audio-Video Generation Audio-Visual Alignment RL for Diffusion Models RL for Generative Models

Sep 22, 2026cs.CL

Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models

Diffusion Large Language Models (dLLMs) have emerged as an efficient alternative to autoregressive models, yet aligning them via Reinforcement Learning (RL) requires likelihood surrogates estimated from masked reconstruction subproblems under a small Monte Carlo budget per rollout. Existing methods construct these subproblems by uniform random masking, leaving open the question of which subproblems to prioritize. We identify a systematic upstream/downstream structure in dLLM rollouts. Some tokens, when revealed, trigger large confidence changes in nearby undecoded positions; we call them upstream. Others induce only small local changes and are therefore downstream. We find masking downstream tokens yields substantially better-posed subproblems than masking upstream tokens, a phenomenon we term subproblem difficulty asymmetry. Based on the observation, we propose Informed Masking (IM), which derives a per-token priority score from the denoising trajectory at zero extra inference cost and biases mask sampling toward downstream tokens. IM is plug-and-play: when plugged into three state-of-the-art dLLM RL methods on LLaDA-8B-Instruct, it delivers up to 2.01%, 8.68%, and 5.77% relative average gains on math and planning benchmarks with improved training stability.

Xiaoyi Yu, Enver Sangineto, Pei Fu +6

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · MiLM Plus, Xiaomi Inc., Beijing, China · University of Modena and Reggio Emilia, Italy +1

RL for Diffusion Models Diffusion Language Models

Sep 14, 2026cs.LG

CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models

Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use tasks. While Reinforcement Learning (RL) has recently been applied to enhance DLMs, standard RL approaches suffer from an exploration bottleneck. To address this, we inject reasoning priors from a stronger teacher model to guide RL exploration. In this paper, we introduce CanvasAnneal, a curriculum-guided diffusion RL framework. During the initial RL phase, we warm-start exploration by injecting teacher-generated reasoning traces into the initial diffusion canvas. As training progresses, we gradually remove this guidance and require the model to generate more of the reasoning trajectory independently. Across mathematical reasoning and tool-use benchmarks, CanvasAnneal improves over standard diffu-GRPO on MATH500, Countdown, and Tau2 and substantially accelerates reward improvement on several tasks, while gains are task-dependent. Our results suggest that structured training-time guidance can alleviate exploration bottlenecks in diffusion RL and speed up convergence on harder tasks.

Blake Olson, Yuhang Song, Emmett McQuinn +1

Google DeepMind

RL for Language Model Reasoning Curriculum RL LLM-Guided RL RL for Diffusion Models Diffusion Language Models

Sep 10, 2026cs.RO

DIA: Denoising Intermediate Advantage for Diffusion Policy Optimization

Diffusion-based robot policies have become widely used in robotic manipulation, where they are typically trained with behavior cloning. However, policies trained purely from demonstrations are limited by the quality and coverage of the available data. Reinforcement learning can further improve the performance of these pretrained policies through interaction. A common approach is to use policy-gradient methods that formulate diffusion-policy fine-tuning as an outer environment MDP together with an inner denoising MDP. However, existing methods typically assign the same environment-level credit to all denoising steps used to construct an action chunk, without distinguishing which intermediate decisions contributed most to the final return. We introduce Denoising Intermediate Advantage (DIA), a policy-gradient method that learns a value function over partially denoised actions and uses it to construct a denoising level advantage for each step of the generative process. DIA combines this inner credit signal with the standard environment-level PPO advantage, providing state-dependent credit throughout the denoising chain. Across Robomimic, FurnitureBench, Franka Kitchen, and D3IL, DIA consistently improves final performance over existing diffusion-policy fine-tuning methods. Beyond final reward, DIA reaches successful states more efficiently and can shift farther from the pretrained behavior distribution, enabling it to discover more effective and efficient task-level strategies and subtask sequences that baseline methods fail to reach.

Arjun Sohal, Yuchi Zhao, Miroslav Bogdanovic +1

University of Toronto, Toronto, ON, Canada · Vector Institute for Artificial Intelligence, Toronto, ON, Canada · Acceleration Consortium, University of Toronto, Toronto, ON, Canada +2

RL for Robotics Step-Level Credit Assignment in RL Diffusion Policy RL for Diffusion Models Policy Learning

Sep 3, 2026cs.LG

LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL

Diffusion reinforcement learning (RL) has recently achieved significant success in post-training image and video generative models. However, most diffusion RL methods, including DanceGRPO and FlowGRPO, recompute selected timesteps with gradient tracking after rollout. Under on-policy training with the same backend for rollout and update, this recomputation is mathematically redundant. Intuitively, the rollout and policy update steps can reuse the same feed-forward backbone to avoid redundant computation, but doing so can incur a large memory overhead during rollout. To address the issue, we present LeanGRPO by restructuring the data-parallel layout and introducing two recompute-free training schedules for trajectory-logprob diffusion RL: (1) LeanGRPO-Retain enables gradient tracking during rollout and directly reuses the resulting computation graphs and saved activations for backward during update, requiring no recomputation; and (2) LeanGRPO-Reweight also enables gradients during rollout, but immediately backpropagates each selected step using a provisional advantage and delays gradient synchronization, then corrects the provisional gradients with the true advantage after the trajectory is completed. These schedules target different model scales and input sizes. Across FlowGRPO/DanceGRPO with FLUX.1-dev and Wan, LeanGRPO achieves up to 1.83x end-to-end speedup while preserving the original optimization objective.

Sijie Wang, Zhiqiang Tan, Xinrui Yang +1

School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen

RL for Diffusion Models RL Post-Training Diffusion Model Acceleration Memory-Efficient Training

Aug 14, 2026cs.LG

Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View

Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matching methods train on reward-labeled noising versions of the rollout samples. This paper shows that these seemingly different losses arise from a single path-space principle. Starting from the regularized diffusion-RL objective, we use importance sampling between sampling SDEs to obtain an explicit policy-gradient estimator on trajectory space. The estimator contains the stochastic Itô integral underlying Flow-GRPO-type updates; we derive an equivalent variance-reduced value-gradient form that recovers the forward-matching structure of AWM and DiffusionNFT. This identifies the empirical gap between these method families as a variance-reduction effect rather than a difference in RL principle. The derivation yields a unified design space organized by value-gradient estimation, weight functions, and sampling choices. Within this space, we propose a multi-sample KDE value-gradient estimator that reuses rollout groups, together with scale-bounded weight families that retain stable existing recipes while excluding singular ones. Experiments on SD3.5-M and Qwen-Image models validate the variance-reduction explanation and show that the resulting recipe improves over prior diffusion-RL baselines.

Yixian Xu, Yuanrui Zhang, Shengjie Luo +2

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · ByteDance Seed

Diffusion Model Alignment Policy Gradient Methods RL for Diffusion Models Variance Reduction

Aug 10, 2026cs.CV

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide distillation supervision. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage co-training framework in which a decoupled student learns from the evolving RL teacher's trajectories without changing teacher optimization. Advantage-Modulated Distillation (AMD) transforms rollout advantages into signed weights, strengthening imitation of preferred trajectories and aligning distillation priorities with task value. The resulting framework is general and lightweight, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment demonstrate competitive few-step, CFG-free generation with RAM or DiffusionNFT teachers. With only four sampling steps, REST-RAM achieves a DrawBench PickScore of 23.97, outperforming both the 40-step RAM teacher (23.95) and RTDMD (23.71).

Yuhan Li, Fangao Zeng, Sicong Kang +7

Shanghai Jiao Tong University · Taobao & Tmall group of Alibaba

Diffusion Model Distillation Few-Step Diffusion Sampling RL for Diffusion Models

Aug 7, 2026cs.CV

PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model

While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement Learning (RL) enables targeted optimization, existing methods are generally constrained by low-efficiency fine-tuning and sparse rewards. To address these challenges, we propose PAST, which provides differentiated rewards while adaptively regulating training episode length by jointly perceiving denoising progress and prompt difficulty. Specifically, we design an intrinsic reward paradigm to compensate for sparse extrinsic rewards and guide the model to explore paths that diverge more efficiently from noise patterns. We further provide theoretical justification for intrinsic rewards. Then, PAST dynamically monitors denoising completion and semantic alignment between image structures and prompt semantics. When both metrics satisfy generation requirements, the system adaptively terminates training. This enables appropriate allocation of episode lengths based on prompt difficulty and the current generation process. Finally, based on the predicted residual noise level, we establish a dual adaptive coordination mechanism. Specifically, it not only balances the extrinsic and intrinsic rewards but also balances the exploration and convergence. Experimental results demonstrate that PAST enhances computational efficiency of existing RL fine-tuning methods by up to 66.7%, while improving preference optimization quality by up to 29.5% through its dual adaptive regulation mechanism.

Renye Yan, Jikang Cheng, You Wu +4

Peking University Beijing, China

Intrinsic Reward Methods Reinforcement Learning Diffusion Sampling Diffusion Model Fine-Tuning RL for Diffusion Models

Aug 7, 2026cs.CV

Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promising but limited by reward sparsity. Since a single reward cannot support optimization, existing RL methods usually backpropagate the final reward to all previous steps. However, denoising is stage-wise, with distinct semantics and controllability. Repeating the final reward across all steps creates a temporal objective mismatch, encouraging reward shortcuts that lead to reward hacking. At the same time, due to reward backfilling, each time step receives the same reward, making it impossible to distinguish between actions, thereby weakening the optimization process. To resolve this issue, we propose Stage-Guided Per-Step Optimization (SGPO) for diffusion models, which jointly leverages signal-to-noise ratio and semantic changes to identify generation stages and adaptively assign stage-specific objectives. Early denoising is chaotic and far from the final reward, resulting in weak reward-behavior correlation. This stage should prioritize exiting the chaotic state. In the mid stage, the latent transitions to a stable structure, where the final reward better corresponds to generative behavior. Therefore, this stage optimizes the final reward while exploring diversity to avoid early convergence to a single mode. In the late stage, the latent's core structure is largely fixed, and preference optimization mainly amplifies local details, risking overfitting. Therefore, stable convergence is preferred to avoid quality degradation. Results from 16 comparative experiments validate SGPO. Our method achieves 26.7% average gains in generative quality and 36.7% higher convergence speed.

Renye Yan, Jikang Cheng, You Wu +4

Peking University Beijing, China · Stanford University Stanford, California, USA

Diffusion Model Alignment Temporal Credit Assignment RL for Diffusion Models

Aug 5, 2026cs.LG

Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control

Diffusion policies are a powerful policy class for continuous control, but their iterative denoising process creates a substantial computational bottleneck. Reducing this cost requires adapting the number of denoising steps to the difficulty of each action while preserving task performance. We introduce Prefix-Optimal Generative Policies (POGP), a framework that learns a prefix value function at every intermediate denoising step through a Bellman-style recursion over the denoising chain. The prefix value function serves two purposes: it provides an auxiliary training objective that encourages intermediate outputs to become high-quality actions, and it enables a test-time stopping rule that terminates denoising when additional steps are unlikely to produce meaningful improvement. Across four MuJoCo environments and comparisons with 12 baselines, POGP reduces the required number of denoising iterations by approximately 2.7-fold while retaining near-full task performance. Compared with state-of-the-art dynamic diffusion baselines, prefix training also improves final task performance by approximately 3.5%. These results indicate that supervising intermediate denoising steps is useful not only for adaptive early stopping, but also as an auxiliary objective that improves the learned policy.

Rohit Kumar Salla, Manoj Saravanan, Simon Stepputtis

Virginia Polytechnic Institute and State University (Virginia Tech), Blacksburg, Virginia, USA

Diffusion Policy Continuous Control RL for Diffusion Models Policy Learning Diffusion Models

Aug 4, 2026cs.LG

Latent Reward Registers for Diffusion Preference Alignment

Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process. We propose Latent Reward Registers, a mechanism that estimates terminal preference directly from intermediate noisy latents by prepending learnable, position-free register tokens to the input sequence of a frozen Diffusion Transformer (DiT). This independent readout mechanism extracts latent reward evidence without altering the generator's hidden states or velocity field. The resulting dense, differentiable reward signal throughout the full denoising process facilitates two alignment strategies. For training, Reward-Gradient On-Policy Distillation (RG-OPD) distills reward-guided updates along on-policy trajectories, bypassing the computationally expensive rollouts of standard policy gradients. For inference, Reward-Guided Sampling (RGS) steers trajectories via magnitude-matched reward gradients without parameter updates. Empirically, at high noise levels (u = 0.8), the registers reach the highest pairwise accuracy among the evaluated latent reward models. Furthermore, RG-OPD outperforms online reinforcement learning baselines while reducing GPU hours by up to 33x, and RGS establishes a new state-of-the-art among training-free methods, strictly enhancing both alignment and perceptual metrics. Code and weights are available at https://github.com/Guanys-dar/latent-reward-register

Yuanshen Guan, Zipeng Feng, Chengru Song +2

1Kling Team · University of Science and Technology of China

Diffusion Model Alignment Diffusion Model Guidance RL for Diffusion Models

Aug 3, 2026cs.LG

Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models

Recent reinforcement learning methods for diffusion large language models (dLLMs) commonly rely on on-policy rollouts generated by the target dLLM itself. When successful on-policy rollouts are scarce, however, on-policy training may receive little positive reward and make only limited progress. To mitigate this problem, we explore incorporating higher-reward rollouts generated by a stronger external policy alongside on-policy rollouts from the target dLLM. However, directly incorporating these external rollouts introduces two practical challenges: differences in rollout length and instability when jointly processing rewards from on-policy and external rollouts. To address these challenges, we propose External Rollout Integration with Length Control and Source-Specific Processing (ERILS), which controls external-rollout length and processes the rewards of on-policy and external rollouts separately. Experiments on Sudoku, Countdown, and MATH500 under zero-shot evaluation show that ERILS improves multi-sample performance across all three tasks, with the largest gains on Sudoku. On Sudoku, ERILS achieves 98.4% best-of-4 completion accuracy, compared with 40.3% for the strongest baseline. ERILS also maintains approximately 90% deterministic single-completion accuracy on Sudoku across generation lengths of 128, 256, and 512 tokens. Our component analysis further shows that length-controlled external rollouts are more effective than uncontrolled external rollouts, and that source-specific reward processing avoids the training collapse observed with joint reward processing. These results show that rollout construction and reward processing are important design dimensions when integrating external rollouts into dLLM reinforcement learning.

Wonseok Lee, Jimyeong Kim, Jungmin Ko +1

Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, South Korea · Artificial Intelligence Institute, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, South Korea · Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, South Korea

RL for Language Model Reasoning RL for Diffusion Models Diffusion Language Models Off-Policy RL

Jul 26, 2026cs.LG

Learning Sampling Parameters for Diffusion Models

Text-to-image diffusion models expose many inference-time sampling parameters, including prompts, negative prompts, classifier-free guidance scales, and noise schedules. These parameters are typically manually chosen once and then held fixed across prompts and denoising timesteps, even though different prompts and stages of generation can benefit from different parameter values. We introduce LeSAMP, a framework for learning prompt-conditioned, timestep-varying sampling parameters. We formulate parameter selection as a reinforcement learning problem: Given a user prompt, a large language model is trained to emit schedules for the chosen sampling parameters. We optimize our model using rewards from human preference models and VLM-as-a-judge. We evaluate our model on Flux.1 [dev] and Stable Diffusion 3.5, and find that compared to baselines, LeSAMP has a win rate of up to 68.12% using human preference scores and 73.37% using VLM-as-a-judge. These gains are validated in a user study where we achieve win rates of up to 59.46% over previous baselines. Our results suggest that learned sampling-parameter policies provide a complementary approach to existing post-training methods for improving diffusion model outputs.

Arisrei Lim, Yossi Gandelsman

Reve

Diffusion Model Guidance Diffusion Model Sampling RL for Diffusion Models T2I Diffusion Models

Jul 20, 2026cs.LG

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive. Training-free DiT inference acceleration methods (e.g.,

Δ

-DiT, ScalingCache) exploit the fact that DiT hidden states and velocity predictions vary \emph{smoothly and nearly linearly} along the trajectory. We ask whether the same linearity can reduce the backward-pass cost of DiT RL training, and answer affirmatively with \textbf{JAGG} (\textbf{J}acobian-\textbf{A}ggregated \textbf{G}roup \textbf{G}radient), which reduces full transformer backward passes from

W

to

2

per group of

W

consecutive steps. JAGG approximates intermediate-step Jacobians via

t

-weighted interpolation of the endpoint Jacobians, then aggregates per-step upstream signals into two composite gradients applied through a single joint backward pass. We prove this interpolation is \emph{exact} when the velocity is linear in

(z,t)

, and a cosine-similarity routing rule (\texttt{jagg_frac}) deploys JAGG only where the assumption holds. Experiments on T2I benchmarks show JAGG delivers

\sim

2

\times

backward speedup with negligible quality degradation. The code for this work can be accessed through https://github.com/SchumiDing/JAGG.

Ruiyi Ding, Jie Li, He Kang +3

1KlingAI Research · University of Science and Technology of China · 2Fudan University +2

Backpropagation Diffusion Transformer T2I Generation Group Relative Policy Optimization RL for Diffusion Models Diffusion Model Acceleration

Jul 20, 2026cs.AI

Reinforcement Learning: From Algorithms To Foundation Models

Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and reasoning over high-dimensional worlds. This thesis studies RL from two perspectives: algorithms in games and RL in the era of foundation models. The first part focuses on multi-agent RL in games. It examines how incentives, policies, and equilibrium concepts interact in competitive and general-sum environments, spanning two-player zero-sum games, large-scale video games, and multi-player settings with general structure. These works investigate learning in multi-agent systems and the behavior of RL methods in interactive environments. The second part studies RL with generative and foundation models, motivated by the idea that prior knowledge can enrich sequential decision making. Pretrained generative models and learned world models serve as representation tools and structured priors for planning, control, and policy optimization. The thesis develops diffusion-based world models, investigates RL for efficient video generation, explores generative models as policy classes, and studies interactive video world models in which actions shape future observations. It also addresses long-horizon modeling through architectures with memory. Together, these contributions present a unified view of RL as objective-driven adaptation in complex sequential domains. From strategic games to generative world models, the thesis highlights how RL connects decision making, environment modeling, and emerging foundation-model capabilities, offering a broader perspective on the principles underlying intelligent behavior.

Zihan Ding

Department of Electrical Computer Engineering, Princeton University

Reinforcement Learning RL for Video Generation RL for Diffusion Models RL for Generative Models Multi-Agent Reinforcement Learning Model-Based RL

Jul 16, 2026cs.CL

Mask-Aware Policy Gradients for Diffusion Language Models

Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation. Existing approaches approximate this log-likelihood by modeling only the token predictions, ignoring the order in which positions are unmasked during generation. We observe that MDLM generation involves two decisions at each step: what tokens to place at each masked position and which positions to remask. We formalize this as a two-stage action MDP, showing that the policy gradient naturally decomposes into a token term and a masking term. Combining optimization of both terms leads to state-of-the-art outcomes on mathematical reasoning and coding benchmarks, with scores of 87.1% on GSM8K and 53.4% on MBPP.

Haran Raajesh, Kulin Shah, Adam Klivans +1

Department of Computer Science The University of Texas at Austin

Masked Diffusion Models RL for Language Model Reasoning Policy Gradient Methods RL for Diffusion Models