This work proposes REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage RL-distillation co-training framework that attaches a decoupled student to an arbitrary RL teacher that enables few-step CFG-free inference that matches or surpasses its 40-step RL teacher, with an overall additional training cost below 25% over pure RL.
Abstract
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 instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage RL-distillation co-training framework that attaches a decoupled student to an arbitrary RL teacher. The student learns segment-wise from the teacher's evolving rollout trajectories while leaving the original teacher optimization unchanged. To prevent uniform imitation from preserving undesirable low-reward behaviors, we further introduce Advantage-Modulated Distillation (AMD), which transforms rollout advantages into signed weights over a base distillation loss. AMD strengthens supervision from preferred trajectories and mildly repels the student from low-reward ones. The resulting framework is lightweight and plug-and-play, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment show that REST enables few-step CFG-free inference that matches or surpasses its 40-step RL teacher, with an overall additional training cost below 25% over pure RL. REST improves DrawBench PickScore over RTDMD by 0.82 while requiring only one-fifth of the training iterations.
Achieving simultaneous preference alignment and distillation acceleration in video diffusion models remains an open challenge. Existing methods optimize the two objectives over mismatched representation spaces, where improving one objective often compromises the other. To overcome this, we propose Reward Lightning, a unified framework that aligns and accelerates a video diffusion model within a single shared representation. Its central principle is homology: both objectives are evaluated on identical latent features, which mitigates the gradient conflicts that arise when they are optimized over disjoint representations. As a foundational component, we first introduce a latent reward model (LRM) that scores videos directly in the latent space, without decoding back to the pixel space. Building on the LRM, homologous preference distillation (HPD) reuses this shared backbone to perform adversarial distillation and preference alignment jointly, yielding few-step generators that remain faithful and well aligned. Extensive experiments demonstrate that the LRM surpasses pixel-level and latent-level reward baselines by $11.0\%$ and $14.7\%$ in preference accuracy, and that Reward Lightning generates high-fidelity videos in merely $1$ to $4$ steps, improving the average VBench score by $2.1\%$ while leading in text alignment, motion quality, and visual quality. Project page: https://reward-lightning.github.io.
Jiaxiang Cheng, Bing Ma, Xuhua Ren et al.· 0 citations
The sample efficiency and scalability of RL post-training for video MLLMs and introduces OraRL, a decoupled advantage estimator that scales with model size and data, surpassing its backbone from 0.8B to 9B and GRPO up to 100k prompts.
Yunheng Li, Guohong Mu, Hao Li et al.· 0 citations
In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. Instead of asking the MLLM to judge a generated image or answer decomposed verification questions, SpectraReward measures how well the original prompt can be recovered from the generated image through a single image-conditioned, teacher-forced forward pass. We use the average image-conditioned prompt log-likelihood as the reward, directly reusing the MLLM's pretrained image-text alignment ability without preference labels, reward-model fine-tuning. We further introduce Self-SpectraReward, a special case for unified multimodal models where the policy's own understanding branch serves as the reward model for its generation branch, forming a closed-loop self-improving framework without external reward models or external knowledge. Extensive experiments validate SpectraReward through a broad image-generation RL study covering two diffusion models, three RL algorithms, nine reward MLLM backbones from four MLLM families spanning 4B to 235B parameters, and five out-of-distribution text-to-image benchmarks. Results show that both SpectraReward and Self-SpectraReward significantly and consistently improve generation performance and outperform prior MLLM-derived reward training methods. Further analysis reveals that larger reward MLLMs are not always better, while Self-SpectraReward can match or surpass much larger external reward models, suggesting that reward-policy alignment is a key factor for effective image-generation RL. Project Page: https://huangrh99.github.io/SpectraReward/
Runhu Huang, Qihui Zhang, Zhe Liu et al.· 0 citations
Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information. This dilemma motivates the transfer of the reasoning capabilities of large models to smaller, more efficient ones. On-Policy Distillation (OPD) offers a promising solution by matching output-token distributions along student-generated trajectories. However, video reasoning often depends on evidence accumulated across multiple frames. In this context, output-level supervision only captures information expressed through token predictions and does not directly constrain the latent representations formed during reasoning. To address this limitation, we propose Latent-OPD, which augments OPD with trajectory-level latent distillation. Specifically, our method focuses on the position at the end of each trajectory, where hidden states effectively summarize the accumulated visual evidence and reasoning context. Furthermore, we introduce a progressive teacher-lookahead strategy, which aligns middle-to-late student layers with increasingly deeper teacher layers. Experiments on six video reasoning benchmarks show that Latent-OPD consistently outperforms output-only OPD. Notably, the improvements are particularly pronounced in scenarios with limited frames, long videos, or tasks requiring complex evidence aggregation. These results establish Latent-OPD as a highly effective approach to frame-efficient video reasoning.
Aoni Shen, Yongheng Zhang, Yinghui Li et al.· 1 citation
Noise-Contrastive GRPO is introduced, which injects scale-calibrated Gaussian noise into the last hidden layer of the prompt-encoding pass for half of each rollout group, branching those rollouts from a displaced departure state and integrates into a standard RLVR pipeline as a ~50-line change to the inference engine.
Michael M. Jerge, Joseph Pelczar, J. Downes· 0 citations
RSTG (Recovering Learning Signals via Adaptive Teacher Guidance), which applies distillation selectively and precisely where it matters most, and substantially outperforms naive GRPO+OPD.
Zhuowen Han, Jinwei Xiao, Zhengxi Lu et al.· 3 citations