Diffusion-Based Reinforcement Learning Methods

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.

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.

Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy can discourage actions having high critic values with low behavior density. Directly refining behavior proposals may be an alternative, yet Gaussian or deterministic editors limit expressiveness to represent multiple separated modes for the same proposal. In this work, we introduce Proposal-Conditioned Refinement Flows (PReFlow), a policy extraction method combining critic-based proposal selection with a conditional refinement flow. To optimize proposal selection and refinement together, we formulate a KL-regularized objective whose optimum induces a Gibbs policy over final actions under a Gaussian-smoothed behavior prior. The refinement flow can represent multiple high value modes, while a proposal-centered Gaussian reference regulates large action changes. This Gaussian reference further enables us to make use of simulation-free, closed form adjoint matching targets from sampled endpoints and critic gradients, yielding a single velocity regression loss without a backward adjoint solve. On 50 OGBench tasks, PReFlow achieves competitive offline performance and the highest aggregate score among the compared methods after online fine-tuning, reaching 91% after 500K environment steps.

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.

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

In social navigation, modeling the complex interactions between humans and robots is difficult, and deep reinforcement learning has therefore been actively studied. However, because simulation alone cannot fully reproduce diverse scenarios, robot dynamics, and the social conventions that vary across deployment environments, fine-tuning in the deployment environment is promising. In doing so, learning that preserves the base model's performance is required, so as not to compromise the primary objective of navigation, namely avoiding pedestrians and reaching the destination. In this study, we propose a method that applies diffusion steering via reinforcement learning (DSRL), which trains only the noise policy while keeping the diffusion policy fixed, thereby achieving learning that preserves performance. Furthermore, we integrate diffusion-based RL policies trained with multiple seeds to construct the base policy, improving learning performance. Our evaluation shows that, compared with other methods, the proposed method enables efficient learning while preserving performance, and we confirm flexible behavior control through adaptation to social conventions, as well as its effectiveness on a physical robot through hardware-in-the-loop simulation.

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.

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.

Multi-AUV ad-hoc network-based target tracking requires networked autonomous underwater vehicles (AUVs) to cooperatively track maneuvering targets under constrained acoustic communication, dynamic topology, and uncertain ocean disturbances. Although multi-agent reinforcement learning (MARL) enables decentralized coordination through centralized training, existing methods suffer from high-dimensional joint state-action modeling, noise-sensitive policy generation, leading to unstable training and degraded tracking. To address these issues, we propose VGG-MADiffRL, a value-gradient-guided multi-agent diffusion RL algorithm, and MDCA, a diffusion?based hierarchical control architecture. Leveraging underwater mission characteristics, we model sonar detection mechanisms and ocean current disturbances, formulating cooperative tracking for multi-AUV ad-hoc networks as an MDP. The proposed MDCA constitutes a three-tier closed-loop control framework: a global intelligent control layer, a local online training layer, and a physical action execution layer. This structure enables synergistic optimization across task allocation, local decision processes, and execution feedback. Within MDCA, the local online training layer is the policy learning framework; VGG-MADiffRL builds on diffusion policies and incorporates value gradients to guide action generation in the reverse denoising process, steering the generated actions towards higher expected returns. It employs twin value networks with joint optimization and soft target updates to mitigate overestimation and training oscillations, promoting more stable convergence. Experimental results show that VGG-MADiffRL consistently achieves faster convergence, higher tracking accuracy, and smoother training dynamics in cooperative tracking scenarios, validating its effectiveness and practical engineering value in dynamic underwater settings.

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).

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.

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.

Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suited to a single nominal robot. This limits the policy's generalization to diverse embodiments and challenging scenarios (e.g., escaping dead ends or detouring long obstacles) that demand diverse local reactive behaviors with only onboard local observations. Post-training the policy with reinforcement learning (RL) offers a principled remedy. However, previous RL for diffusion approaches lead to only marginal improvements. This is because the intractable likelihood of diffusion policies renders policy gradients unstable in addition to inefficient policy exploration. To address these challenges, we propose a data-efficient diffusion RL post-training framework - GQRM (Group Q-score Reweighted Matching). Our framework introduces two complementary designs: (i) a self-bootstrapped exploration strategy with behavior perturbation that preserves the pretrained policy prior, and (ii) a group Q-score normalization mechanism that computes per-trajectory values on each state for efficient reweighted score matching. By conducting distributed online RL training across heterogeneous embodiments, the resulting fine-tuned policy, X-NavDP, achieves state-of-the-art cross-embodiment visual navigation performance, improving the overall success rate from 61.20% to 84.28% in simulation and 10% to 65% in real-world hard cases. The code and model are publicly available at https://yty-sky.github.io/x-navdp-project-page.

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

Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences. However, applying RLHF to diffusion models remains highly feedback inefficient, as existing approaches typically require large amounts of human or reward model evaluations. This limitation reduces the practicality of diffusion RLHF in realworld settings where feedback is the primary bottleneck. In this paper, we propose two complementary strategies that substantially improve the feedback efficiency of diffusion RLHF while preserving generalization to unseen prompts. Our key observation is that reward information in diffusion trajectories is unevenly distributed: not all denoising timesteps or trajectories contribute equally to learning from a reward signal. By emphasizing informative timesteps and trajectories during optimization, we obtain more effective gradient updates. First, we introduce a per-timestep weighting scheme that reweights denoising steps during policy optimization. We theoretically connect this weighting to the optimal convergence properties of proximal policy optimization (PPO) and approximate the resulting weighting trend empirically. Second, we introduce a replay mechanism that prioritizes informative trajectories, enabling the model to reuse past samples instead of repeatedly querying new rewards. Together, these strategies significantly improve the feedback efficiency of diffusion RLHF. Under identical hyperparameter settings, our approach achieves up to a 6$\times$ improvement in sample efficiency compared to widely used diffusion RLHF baselines.

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

Offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction, making it appealing for safety-critical applications where online exploration is costly or unsafe. Diffusion-based decision-making methods have recently achieved strong performance in offline RL by modeling rich, multimodal trajectory distributions. However, existing diffusion planners are typically risk-neutral and therefore may overlook rare but catastrophic outcomes that are crucial in real-world deployment. In this work, we propose RS-Diffuser, a risk-sensitive offline diffusion planning framework that combines diffusion-based trajectory generation with distributional value critics. RS-Diffuser learns a diffusion planner over future state trajectories, a separate inverse dynamics model for action decoding, and a Monte Carlo distributional critic that estimates the full return distribution of candidate plans through quantile regression. At sampling time, we incorporate a risk-sensitive guidance signal into the denoising process, using gradients computed from tail-aware objectives such as Conditional Value at Risk to steer generation toward desired risk profiles. As a result, a single trained model can flexibly produce risk-averse, risk-neutral, or risk-seeking behaviors by changing only the inference-time risk parameter. Extensive experiments on risk-sensitive D4RL and risky robot navigation benchmarks demonstrate that RS-Diffuser achieves state-of-the-art performance, improving both overall return and worst-case robustness while reducing safety violations.

Reinforcement learning (RL) has become a dominant post-training paradigm, driving the emergence of high-performance RL systems such as veRL for autoregressive large language models (LLMs). In parallel, diffusion-oriented RL algorithms, e.g., DanceGRPO and FlowGRPO, have rapidly expanded the scope of RL from language reasoning to diffusion-based visual and flow-based generation. However, efficient RL systems for diffusion generative LLMs remain underexplored. Existing implementations, e.g., veRL-Omni, still rely on colocated execution, which simplifies synchronization but couples rollout and training resources, limits heterogeneous deployment, and constrains independent scaling. To this end, we introduce DigenRL, a disaggregated RL framework for diffusion-based generative LLMs that supports flexible resource allocation, accommodates heterogeneous GPUs, and facilitates efficient task scheduling. To maximally reduce the execution bubbles in the disaggregated architecture, we propose: 1) a generation-axis pipeline (GAP) and time-step parallelism (TSP) in the diffusion architecture to enable finer-grained pipelining between rollout and training; 2) an elastic trainer-assisted generation (TAG) approach to enable the trainer GPU resources to dynamically assist in executing rollout generations; and 3) a tightly one-step constrained asynchronous strategy to further utilize the tail bubble in the pipeline. Extensive experiments are conducted on three hardware testbeds with 16-32 GPUs using HunyuanVideo-13B, Wan2.1-14B, FLUX.1-12B, and QwenImage-20B generative models. Experimental results show that DigenRL achieves 1.56-2.10x throughput improvements over state-of-the-art diffusion RL systems, veRL-Omni and GenRL.

Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of scalable training in the absence of ground-truth data, where standard optimization techniques such as score matching are not directly applicable. In this work, we introduce a highly efficient algorithm for optimizing diffusion policies by leveraging recent advances in stochastic optimal control. Our approach is based on adjoint matching, which enables simulation-free training and circumvents the need for explicit likelihood estimation or costly backpropagation through the diffusion process. Furthermore, we propose several extensions that improve the robustness and stability of the method in practical settings. Empirical results demonstrate that our approach achieves competitive performance while significantly reducing computational overhead, making diffusion policies more viable for online RL scenarios.

Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selecting high-contrast samples, yet adds compute to the critical path; spot GPUs offer 69--77% lower cost, yet sit idle during training because DiT rollouts finish nearly simultaneously, which prevents LLM-style pipelining of rollout with training. Spot preemptions further break Sequence Parallelism (SP) groups, fragmenting GPU topology. We present Spotlight, the first system that harvests spot GPUs for DiT RL post-training. Spotlight rests on two key insights we devise: (1)~we show that exploration can tolerate stale model weights because exploration that uses the model weights from the previous iteration preserves the relative ranking of random seeds, allowing exploration to run on idle spot GPUs during training. (2)~SP reconfiguration can reuse on-node state, reducing group recovery from minutes to sub-second launches. Built on these insights, Spotlight introduces three techniques: a bandit-based exploration planner that maximizes reward variance within the training time budget, elastic sequence parallelism that reconfigures SP groups on the fly via persistent schedulers and intra-node weight copying, and a preemption-aware pull-based request scheduler that balances load and commits in-flight state upon preemption. We implement Spotlight on the open-source RL platform ROLL and evaluate it on Qwen-Image post-training. Spotlight reaches the same target validation score $4\times$ faster than baselines, reducing total cost by $1.4$-$6.4\times$ while achieving superior image quality on DeepSeek-OCR and Geneval datasets with resolution $512\times512$ and $1280\times1280$.

The integration of generative artificial intelligence with wireless communication and signal processing systems has opened new avenues for intelligent, data-driven decision-making in future 6G networks. This work proposes a diffusion soft actor-critic (Diffusion-SAC) approach that leverages offline reinforcement learning (RL) enhanced by denoising diffusion probabilistic models (DDPMs) to optimize trajectory and scheduling control in unmanned aerial vehicle (UAV) networks. While offline RL methods, such as conservative Q-learning (CQL), can learn from static datasets, they often struggle to generalize in low-data or dynamic conditions. To address this, we combine the robustness of CQL with the generative power of diffusion models, enabling expressive and signal-aware policy learning that generalizes beyond behavior policies. Applied to a UAV-assisted wireless network, the proposed framework minimizes transmission energy and improves fairness among devices. Simulations show that Diffusion-SAC outperforms standard offline RL baselines, achieving more stable convergence and higher rewards even with limited datasets. The method enhances data efficiency, reduces energy consumption, and increases throughput by more than 35 % compared to existing algorithms, demonstrating its potential for robust policy learning in next-generation wireless control systems.

Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely on simple Gaussian policy parameterizations. Diffusion models provide a more expressive policy class and have shown strong performance on challenging control problems, yet most diffusion-based RL methods are designed for offline or off-policy training. In this work, we ask whether diffusion policies can be trained effectively in the massively parallel, on-policy regime. To this end, we introduce Trust-region Diffusion Policies (TruDi), which enables diffusion policies for on-policy RL with massively parallel simulations. This setting is particularly challenging because the data distribution changes quickly across updates, making stable training with complex policies difficult. TruDi addresses this by integrating a trust-region optimization rule to enforce a KL-divergence constraint over the entire diffusion trajectory. Empirically, we evaluate TruDi on a diverse set of 4 massively parallel RL benchmarks comprising a total of 73 tasks. Across these tasks, TruDi consistently outperforms or is on-par with strong baselines on standard tasks and achieves clear gains on more challenging humanoid control tasks, establishing a strong new baseline for massively parallel on-policy RL.

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in the supervised imitation learning setting, incorporating them into reinforcement learning (RL) pipelines for policy improvement has proven more difficult. It often requires specialized training objectives or backpropagating through denoising processes, which cause well-known issues with stability and affect scalability. In this paper we study the question of whether simple policy improvement schemes at test time alone, leaving stable supervised policy training intact, can be a competitive alternative which sidesteps these issues. To this end, we propose QGF (Q-Guided Flow), an RL algorithm that performs policy optimization entirely at test time. QGF works by pre-training both a reference flow policy (via a standard behavioral cloning objective) and a value function critic and, at test time, using the value gradient to guide the reference policy to generate higher-value actions without any additional policy learning. Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time algorithms while being much cheaper to run. Moreover, it exhibits favorable scaling with model size by avoiding the instability of actor-critic training, offering a practical and effective alternative RL algorithm with expressive policies.

Diffusion-based Q-learning has emerged as a powerful paradigm for offline reinforcement learning, but its reliance on multi-step denoising makes both training and inference computationally expensive and brittle. Recent efforts to accelerate diffusion Q-learning toward single-step action generation typically introduce auxiliary networks, policy distillation, or multi-phase training, which frequently compromise simplicity, stability, or performance. To address these limitations, we introduce Bootstrapped Flow Q-Learning (BFQ), a novel framework that enables accurate single-step action generation during both training and inference, without auxiliary networks or distillation procedures. BFQ adopts a divide-and-conquer view of the displacement vector along the flow path: it begins by learning short-range displacements that can be accurately estimated from the Flow Matching marginal velocity, and bootstraps these components to directly learn a noise-to-action mapping in a single step. This formulation eliminates multi-step denoising, resulting in a learning procedure that is substantially faster, simpler, and more robust. Extensive D4RL evaluations show that BFQ improves performance while significantly reducing computational cost compared to multi-step diffusion baselines, demonstrating that single-step action generation suffices for high-performance offline Reinforcement Learning.

Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authentic generation trajectory and the gradient update process: (i) Process-reward misalignment. Sparse, terminal rewards are indiscriminately assigned to all intermediate steps of the generation process, failing to provide discriminative credit assignment. (ii) State-trajectory misalignment. Policy updates are often diverted toward artificial, out-of-trajectory states, squandering gradients on less informative samples. To address these limitations, we introduce Process Aligned Policy Optimization (PAPO), a novel framework that holistically aligns the RL update with the dLLM's generative trajectory via Step-Aware Process Rewards (SPR) that transform sparse terminal rewards into dense, step-wise credit, and Entropy-Guided Historical Re-enactment (EHR) that replays authentic trajectories at high-uncertainty steps. Extensive experiments on four benchmarks demonstrate that PAPO significantly outperforms baselines, achieving gains of up to 4.5% on GSM8K, 4.8% on MATH500, 42.2% on Countdown and 16.1% on Sudoku.

Diffusion large language models (dLLMs) generate responses by iteratively unmasking and revising many positions in parallel. This process leaves a rich denoising trace depicting which tokens become confident, which remain unstable, and when commitments form. Existing dLLM reinforcement learning methods use this signal only weakly. Flat rollouts are cheap, but assign a single outcome reward to the whole trajectory. Tree rollouts provide finer, verifiable training signals by branching partial trajectories and propagating leaf rewards upward, but are compute intensive. We ask whether the denoising trace itself can provide tree-like supervision without tree-level compute. We introduce CAPR (Cached-Amortized Path Refinement), a dLLM-RL algorithm that summarizes the denoising trace into a compact path state, uses cached trajectory states to generate cheap sibling continuations, and trains a block-level value head for local block-wise supervision. Under a block-wise unmasking schedule, CAPR records path-state and block-progress features, then redistributes the final outcome reward across blocks according to the tokens revealed in each block. This trains the value head to convert one sparse reward into block-level PPO weights. CAPR therefore recovers much of the granularity of tree search while avoiding full tree expansion, reducing rollout-generation cost to roughly 0.75x that of flat rollouts and 0.6x that of tree rollouts (under standard settings). Across 4x4 Sudoku, Countdown, GSM8K, and Math500, on dense and mixture-of-experts LLaDA backbones, CAPR sets a new state of the art for RL-tuned dLLMs at 256- and 512-token budgets. On Sudoku, it matches the strongest tree-structured baseline at less than one third of the per-step compute.

Offline reinforcement learning requires improving a policy from fixed data while avoiding out-of-distribution actions with unreliable value estimates. Diffusion and flow policies handle this trade-off by modeling the behavior distribution to regularize the RL objective, but they require iterative denoising, solver integrations, and in more efficient variants, distillation or other approximations at inference. We propose DriftQL, which combines a drift-based behavioral regularizer with critic-driven policy improvement. The value signal biases the policy toward high-value regions of the data support, while attraction and repulsion together keep generated actions near the data and prevent collapse onto a single mode. DriftQL is implemented as a single network with a unified training objective and generates actions in a single forward pass. On D4RL and OGBench, DriftQL consistently outperforms diffusion and flow methods, advancing the state of the art. Under degraded data quality, where the baselines visibly struggle, DriftQL remains close to its clean-data performance, positioning it as a promising alternative to diffusion and flow-based methods while maintaining the simplicity and efficiency of deterministic approaches. Project page: https://driftql.github.io/

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based policy optimization. This design enables better exploration capability of the diffusion model, particularly at the beginning of training, but suffer from low exploitation in Q-value information, resulting in a slow policy convergence. Another branch pays attention to gradient-based policy optimization, which sufficiently exploits the gradient of the Q function yet tends to collapse into a unimodal policy with low diversity. To address this issue, we propose CGPO, \textbf{C}ritic-\textbf{G}uided diffusion \textbf{P}olicy \textbf{O}ptimization, which effectively balances exploration and exploitation with the training-free guidance technique integrated into the denoising process of diffusion policy. Concretely, CGPO steers action generation toward high-value regions defined by the critic network and uses the guided actions as regression objectives. In this manner, CGPO reduces the time required to obtain high-quality actions and improves final performance with better balance between the exploration-exploitation tradeoff. We validate the effectiveness of CGPO on 5 MuJoCo locomotion tasks, and CGPO achieves state-of-the-art performance compared with existing diffusion-based RL methods. Notably, CGPO is the first success to incorporate diffusion policy into real-world RL, with its superior performance on Franka robot arm grasping tasks. Our official page is released at https://dingsht.tech/cgpo-webpage.

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.

Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (DLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm that leverages feedback obtained from rollout and training processes to facilitate accurate and efficient policy loss estimation. To balance the trade-off between computational efficiency and estimation effectiveness, RLDF optimizes the model toward the clipped clean state from intermediate noisy states, combined with weighted timestep sampling over denoising timesteps. Extensive experiments demonstrate that RLDF achieves consistent and substantial improvements in both performance and generalizability across two representative DLM architectures, LLaDA and Dream, on multiple reasoning benchmarks. Our work lays a principled foundation for scalable reinforcement learning in diffusion language models. We build Drift, a training framework for DLMs, available at https://github.com/ant-research/Drift.

Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmentation and data filtering are constrained to the source dataset and cannot synthesize new target behavior to improve coverage beyond the collected source trajectories. While recent model-based methods attempt to address this by learning target-aware dynamics, the generated experience is constructed only at the transition level, which leads to accumulated errors over long horizons. These limitations necessitate a shift toward trajectory-level generation for off-dynamics offline RL. We propose CEDGE, a Cross-domain Energy-guided Diffusion GEneration framework. CEDGE trains a trajectory diffusion model on source-domain trajectories and adapts the generated samples to the target domain through energy guidance. This guidance is derived by minimizing the distribution mismatch between the source and desired target-domain trajectories and is decomposed into return, domain, and behavior energy components. The resulting energy-guided trajectories are useful both for direct planning and as synthetic data for policy learning. Since target adaptation is achieved via energy guidance rather than retraining the diffusion model, CEDGE can be efficiently adapted to new target dynamics compared to previous methods. Experiments on the ODRL benchmark demonstrate that trajectory-level energy-guided generation improves diffusion planning under dynamics shifts and produces synthetic data that improves downstream target policy learning.

Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in online RL. MeanFlow offers a promising alternative by learning an average velocity field that maps noise to data in a single network evaluation. However, MeanFlow typically requires samples from the target distribution to construct its target velocity field, which are unavailable in online RL. We propose Score-Based One-step MeanFlow Policy Optimization (SOM), an actor-critic algorithm that resolves this by constructing the target velocity field directly from the Q-function via score estimation and a probability flow ODE, thereby concentrating probability mass on high-value modes. In the fully online RL setting, SOM achieves state-of-the-art performance on locomotion tasks with a single generation step, while substantially reducing both training and inference time compared to prior diffusion- and flow-matching-based policies.

Reinforcement Learning (RL) is an important paradigm for aligning Diffusion Language Models (DLMs) toward functional correctness in code generation. However, these models often encounter a ``capability cliff'' on complex tasks, where execution-based semantic rewards become too low to provide a viable learning signal. In this paper, we present a systematic empirical study of RL post-training for diffusion-based code generation along three axes: reward design, hint-conditioned sampling, and task difficulty. We investigate the effectiveness of execution-free rewards as alternatives to traditional unit-test execution, the role of training-time hint-conditioned diffusion sampling in mitigating exploration bottlenecks, and the impact of these design choices varies across tasks with different difficulty levels. Across HumanEval, MBPP, and LiveCodeBench, we find that static checking is the strongest overall standalone execution-free reward in our setting, especially improving DiffuCoder from 53.9 to 67.1 on HumanEval and from 14.9 to 15.5 on LiveCodeBench while reducing rollout time by 9.4%. We further find that moderate AST-based hinting is most useful on harder benchmarks, while the best reward design depends strongly on task difficulty: similarity-based rewards are more effective on easier subsets, whereas static checking is more reliable on harder subsets where execution rewards are low. These findings suggest that reward design and training guidance substantially affect diffusion RL performance in our evaluated code-generation setting.

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%.

Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synchronization. Reinforcement Learning (RL) offers a promising paradigm, but its extension to multi-objective and multi-modal joint audio-video generation remains unexplored. Notably, our in-depth analysis first reveals that the primary obstacles to applying RL in this stem from: (i) multi-objective advantages inconsistency, where the advantages of multimodal outputs are not always consistent within a group; (ii) multi-modal gradients imbalance, where video-branch gradients leak into shallow audio layers responsible for intra-modal generation; (iii) uniform credit assignment, where fine-grained cross-modal alignment regions fail to get efficient exploration. These shortcomings suggest that vanilla RL fine-tuning strategy with a single global advantage often leads to suboptimal results. To address these challenges, we propose OmniNFT, a novel modality-aware online diffusion RL framework with three key innovations: (1) Modality-wise advantage routing, which routes independent per-reward advantages to their respective modality generation branches. (2) Layer-wise gradient surgery, which selectively detaches video-branch gradients on shallow audio layers while retaining those for cross-modal interaction layers. (3) Region-wise loss reweighting, which modulates policy optimization toward critical regions related to audio-video synchronization and fine-grained alignment. Extensive experiments on JavisBench and VBench with the LTX-2 backbone demonstrate that OmniNFT achieves comprehensive improvements in audio and video perceptual quality, cross-modal alignment, and audio-video synchronization.

Discrete flow models (DFMs) are a class of flexible generative models for generating discrete data, and diffusion large language models (dLLMs) can be viewed as a special case with a specific choice of a mixture path and a masked source distribution. While several recent works have explored reinforcement learning for dLLMs, its application to more general discrete flow models remains underexplored. In this work, we present discrete Flow-GRPO (dFlowGRPO), a unified reinforcement learning framework for discrete flow models that supports a broad family of probability paths and non-masked source distributions. We derive the full trajectory probability for DFMs and formulate the denoising process as a Markov decision process, enabling dFlowGRPO to incorporate information from both the associated conditional transition rates and the posterior model during reinforcement learning. We apply dFlowGRPO to FUDOKI, a recent multimodal discrete flow model, and evaluate it on both image generation and multimodal understanding tasks. Empirical results show that dFlowGRPO outperforms existing GRPO-type methods for dLLMs on text-to-image generation tasks and achieves performance competitive with continuous flow-based models trained using Flow-GRPO, while also demonstrating strong capabilities on understanding tasks.

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.

Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories. While existing paradigms such as Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO) attempt to address this, they are often hindered by either reliance on bias-prone, complex reward models or suboptimal timestep sampling. In this paper, we propose Diffusion-APO (Aligned Preference Optimization), a trajectory-aware algorithm that resolves this misalignment by synchronizing training noise with inference-time denoising paths to maximize gradient signal efficacy. To translate this algorithmic innovation into a practical solution, we introduce a unified and modular RLHF framework that integrates online ranking, half-online anchoring, offline refinement, and distillation-aware drift correction. This framework enables flexible, multi-stage preference alignment across diverse data and computational constraints without relying on scalar-reward-based policy gradients. Through extensive experiments, we demonstrate that Diffusion-APO consistently outperforms standard baselines in visual quality and instruction following, while effectively preserving generative fidelity during model acceleration, providing a robust, end-to-end pathway for scalable video diffusion alignment.

Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates. We identify two fundamental weaknesses: the absence of temporal credit assignment across the denoising trajectory, and the systematic bias of mean-field likelihood estimates used for policy optimization. To address these, we propose Denoising-Aware Credit Assignment for GRPO (DACA-GRPO), a lightweight, plug-and-play enhancement for any GRPO-style trainer. DACA-GRPO introduces two complementary mechanisms: Denoising Progress Scores, which extract per-token importance weights from intermediate predictions at no additional forward cost, and Stratified Masking Likelihood, which partitions token positions into strata so that each token is predicted with most of the sequence as context, reducing the mean-field bias. Applied on top of three GRPO base methods, DACA-GRPO achieves consistent improvements across seven benchmarks spanning mathematical reasoning, code generation, constraint satisfaction, and constrained generation, with gains of up to 5.6pp on math reasoning, 7.4pp on code generation, 36.3pp on constraint satisfaction, and 5.9pp on JSON schema adherence.

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple rewards by training one specialist model per reward, optimizing a weighted-sum reward $R(x)=\sum_k w_k R_k(x)$, or sequentially fine-tuning with a hand-crafted stage schedule. These approaches either fail to produce a unified model that can be jointly trained on all rewards or necessitates heavy manually tuned sequential training. We find that the failure stems from using a naive weighted-sum reward aggregation. This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address this issue, we propose MARBLE (Multi-Aspect Reward BaLancE), a gradient-space optimization framework that maintains independent advantage estimators for each reward, computes per-reward policy gradients, and harmonizes them into a single update direction without manually-tuned reward weighting, by solving a Quadratic Programming problem. We further propose an amortized formulation that exploits the affine structure of the loss used in DiffusionNFT, to reduce the per-step cost from K+1 backward passes to near single-reward baseline cost, together with EMA smoothing on the balancing coefficients to stabilize updates against transient single-batch fluctuations. On SD3.5 Medium with five rewards, MARBLE improves all five reward dimensions simultaneously, turns the worst-aligned reward's gradient cosine from negative under weighted summation in 80% of mini-batches to consistently positive, and runs at 0.97X the training speed of baseline training.

Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct preference optimization (DPO), which avoids explicit reward modeling, has been widely studied. However, its reliance on binary feedback limits it to coarse-grained modeling on chosen-rejected pairs, resulting in suboptimal optimization. In this paper, we propose ArenaPO, which leverages Arena scores as offline rewards to provide refined feedback, thus achieving efficient and fine-grained optimization without a reward model. This enables ArenaPO to benefit from both the rich rewards of traditional RLHF and the efficiency of DPO. Specifically, we first construct a model Arena in which each model's capability is represented as a Gaussian distribution, and infer these capabilities by traversing the annotated pairwise preferences. Each output image is treated as a sample from the corresponding capability distribution. Then, for a image pair, conditioned on the two capability distributions and the observed pairwise preference, the absolute quality gap is estimated using latent-variable inference based on truncated normal distribution, which serves as fine-grained feedback during training. It does not require a reward model and can be computed offline, thus introducing no additional training overhead. We conduct ArenaPO training on Pick-a-Pic v2 and HPD v3 datasets, showing that ArenaPO consistently outperforms existing baselines.

Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates and selecting the best one. In this work, we propose FASTER, a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost by tracing the performance gain of action samples back to earlier in the denoising process. Our key insight is that we can model the denoising of multiple action candidates and selecting the best one as a Markov Decision Process (MDP) where the goal is to progressively filter action candidates before denoising is complete. With this MDP, we can learn a policy and value function in the denoising space that predicts the downstream value of action candidates in the denoising process and filters them while maximizing returns. The result is a method that is lightweight and can be plugged into existing generative RL algorithms. Across challenging long-horizon manipulation tasks in online and batch-online RL, FASTER consistently improves the underlying policies and achieves the best overall performance among the compared methods. Applied to a pretrained VLA, FASTER achieves the same performance while substantially reducing training and inference compute requirements. Code is available at https://github.com/alexanderswerdlow/faster .

Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to UDM leads to training instability and marginal performance gains. To address this, we propose UDM-GRPO, the first framework to integrate UDM with RL. Our method is guided by two key insights: (i) treating the final clean sample as the action provides more accurate and stable optimization signals; and (ii) reconstructing trajectories via the diffusion forward process better aligns probability paths with the pretraining distribution. Additionally, we introduce two strategies, Reduced-Step and CFG-Free, to further improve training efficiency. UDM-GRPO significantly improves base model performance across multiple T2I tasks. Notably, GenEval accuracy improves from $69\%$ to $96\%$ and PickScore increases from $20.46$ to $23.81$, achieving state-of-the-art performance in both continuous and discrete settings. On the OCR benchmark, accuracy rises from $8\%$ to $57\%$, further validating the generalization ability of our method. Code is available at https://github.com/Yovecent/UDM-GRPO.

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To overcome this limitation, we propose to represent policies using MeanFlow models, a class of few-step flow-based generative models, to improve training and inference efficiency over diffusion-based RL approaches. To promote exploration, we optimize MeanFlow policies under the maximum entropy RL framework via soft policy iteration, and address two key challenges specific to MeanFlow policies: action likelihood evaluation and soft policy improvement. Experiments on MuJoCo, DeepMind Control Suite and HumanoidBench benchmarks demonstrate that our method, Mean Flow Policy Optimization (MFPO), achieves performance comparable to or exceeding current diffusion-based baselines while considerably reducing training and inference time. Our code is available at https://github.com/dongxiaoyi-xyz/MFPO.

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is 4.6 times more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method without reward hacking.

Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remains expensive. Typically, this requires thousands of GPU-hours and a large pre-generated trajectory dataset. We introduce ReDiF, which casts step distillation as terminal-reward policy optimization rather than step-wise regression. The student is optimized against a reward computed on the terminal sample, measuring alignment with the teacher's output, instead of matching the teacher's intermediate trajectory under a reconstruction or consistency loss. Because the reward need not be differentiable or trajectory-aligned, ReDiF admits non-differentiable objectives, multi-objective combinations, and preferences the teacher does not express, while exploration lets the student find sampling paths matched to its own step schedule. ReDiF converges in 400 policy updates with 3200 rollouts on a single A100 GPU with 1,000 noise-class pairs and no paired dataset: about 4 GPU-hours, against roughly 336 A100-hours reported for DMD2 on the same EDM teacher. At 8 steps on ImageNet-64, it achieves an FID 3.64 points better than the strongest retrained distillation baseline in the low-training regime under the same single-GPU budget. The formulation is also orthogonal to existing distillation objectives: added to the DMD2 loss, it further improves DMD2's FID by 4.4.

Diffusion models provide an expressive framework for sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion-based policies by introducing Diffusion-Augmented Markov Decision Processes (DA-MDPs). DA-MDPs interpret each reverse-diffusion transition as an individual reinforcement-learning decision, while only the final denoised action is executed in the environment. Our DA-MDPs follow from a principled derivation based on the variational-inference formulation of ME-RL. By augmenting policy and target trajectories with intermediate diffusion variables, we obtain a tractable reverse-KL upper bound via the data-processing inequality. This bound decomposes across denoising transitions, yielding diffusion-augmented variants of soft rewards, value functions, and local policy objectives. This provides a general framework for adapting ME-RL algorithms to diffusion policies while differentiating through only one diffusion transition at a time. We instantiate the framework with PPO, REPPO, and a maximum-entropy extension of WPO. Experiments demonstrate improved continuous-control performance, benefits from additional diffusion steps, and memory-efficient training. On the StackCube and PushT manipulation tasks, DA-MDP methods learn alternative successful strategies from the same initial state and achieve higher success rates and generally higher success-weighted mode entropy than the Gaussian ME-RL baseline. We also demonstrate successful training when using action chunking.

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is crucial to enabling dLLMs to achieve performance comparable to that of AR-LLMs on important tasks, such as reasoning. However, RL algorithms well-suited to dLLMs' unique characteristics have yet to be developed. This paper proposes Distribution Matching Policy Optimization (DMPO), a principled and theoretically grounded RL fine-tuning method specifically designed to enhance the reasoning capabilities of dLLMs by matching the dLLM policy distribution to the optimal, reward-tilted one through cross-entropy optimization. We identify a key implementation challenge with small training batch sizes and propose several effective solutions based on a novel weight baseline subtraction technique. DMPO exhibits superior performance on multiple reasoning benchmarks without supervised fine-tuning, achieving up to a $39.63$ percentage-point improvement in accuracy over prior non-DMPO RL baselines and $67.97$ percentage points over the base model, underscoring the effectiveness of the distribution-matching framework. Our code is available at https://github.com/yuchen-zhu-zyc/DMPO.

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD). DiffusionOPD first trains task-specific teachers independently, then distills their capabilities into a unified student along the student own rollout trajectories. This decouples single-task exploration from multi-task integration and avoids the optimization burden of solving all tasks jointly from scratch. Theoretically, we lift the OPD framework from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies both stochastic SDE and deterministic ODE refinement via mean-matching. We formally and empirically demonstrate that this analytic gradient provides lower variance and better generality compared to conventional PPO-style policy gradients. Extensive experiments show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance, while achieving state-of-the-art results on all evaluated benchmarks.