On-policy distillation (OPD) has recently emerged as a popular post-training paradigm for large language models (LLMs), providing an efficient way to transfer the knowledge and capabilities of teacher models into student models. However, teacher guidance on student-generated prefixes is not always reliable. Training should optimize the model to generate responses that are more likely to be correct, or equivalently, to get higher outcome rewards. But during OPD, the teacher model may provide guidance that discourages the student from moving toward correct trajectories or moves the student toward incorrect ones, which is misaligned with outcome reward. Such misaligned guidance is unreliable, as it would mislead the optimization process and ultimately degrade model performance. To mitigate misaligned teacher guidance, we propose Reward-Aligned On-Policy Distillation (RA-OPD). The key insight is to keep only trajectories whose induced updates move the student toward correct trajectories or discourage the student from moving toward incorrect ones. Specifically, for each sampled trajectory, RA-OPD checks whether its trajectory-level distillation return is consistent with its outcome reward and then filters out the misaligned trajectories. RA-OPD selects more reliable trajectories to improve student model performance without requiring additional computational cost. We evaluate RA-OPD on math and code benchmarks using models from the Qwen3 family and the DeepSeek-R1 family. Across seven math benchmarks and three code benchmarks, RA-OPD significantly outperforms standard OPD and other tested OPD variants.
Discrete diffusion models have become a strong, widely adopted class of generators for sequence data, and steering them toward a downstream reward at inference time, without any retraining, is increasingly important. Such training-free steering is done by gradient guidance, by search, or by combining the two. We study the combined regime and identify two weaknesses in how it is usually run: the guided proposal estimates its gradient from a single noisy sample, and the search then resamples particles at a fixed temperature that ignores how rewards spread across each denoising step. We address both with a small set of changes that add no denoiser cost. For the proposal, we lower the estimator variance with a Rao-Blackwellized reveal for differentiable rewards and a leave-one-out baseline for non-differentiable ones; for the search, we standardize the per-step values into a group-relative advantage and prove it collapses to a single active ingredient, an adaptive resampling temperature. We call the resulting method Guided Reduced-variance proposals and Adaptive Selection (GRAS). GRAS is simple yet effective: across regulatory DNA and protein design it attains the best training-free reward, outperforming prior training-free methods and matching or surpassing a reward-fine-tuned model, and it remains effective even for non-differentiable rewards.
Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries. At each outer iteration, a frozen behavior policy generates trajectories and supplies query states and anchors. Reward gradients construct bounded positive and negative targets around each anchor. The trainable policy fits these targets as detached supervision through finite fitting before an exponential moving average update refreshes the behavior policy. This setup lets us measure target construction and finite realization separately. Controlled same-query experiments show that larger target-construction gains do not necessarily translate into larger realized gains after a single fitting update. Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators. It outperforms the strongest competing method by up to 44.0% and reduces training GPU-hours relative to DiffusionNFT by 40% on SD 3.5-M and 63% on Z-Image-Turbo. These results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.
Synthesizing native 2K multi-garment virtual try-on is a formidable frontier in digital fashion, critically bottlenecked by two fundamental limitations: the O(N^2) memory explosion induced by 2k conditions, and the spectral bias of diffusion models that over-smooths high-frequency fabric details. We present WearWow, an end-to-end, mask-free generative framework that pioneers ultra-high-resolution multi-garment synthesis. To mitigate the memory explosion , we propose Adaptive 2D Token Packing (ATP). ATP leverages inherent garment sparsity to algorithmically pack heterogeneous items onto a unified 2D canvas and prune uninformative background tokens, minimizing the effective sequence length and subsequent memory overhead while rigorously preserving 2D spatial priors. To rectify texture degradation, we introduce the Multi-dimensional Try-on Reward (MTR) system. MTR synergizes a Semantic Guidance Reward to explicitly drive tactile restoration with a Cloth Distribution Reward to implicitly anchor the physical distribution, a joint formulation that effectively mitigates the severe reward hacking. Furthermore, we curate WearWow-2K, an extreme-quality dataset comprising native 2K triplets, providing physically correct spatial interactions that naturally empower the model's mask-free generation. Extensive experiments demonstrate that WearWow establishes a new state-of-the-art, exceeding existing commercial baselines in native 2K multi-garment synthesis.
Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the "Thinking with Images" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism. This design enables the model to adaptively balance internal knowledge and implicit tools, avoiding redundant tool usage while substantially reducing inference latency. Specifically, BEE involves a two-stage training process: (1) Formalized Chain-of-Thought (CoT) Supervised Fine-tuning (SFT). We construct CoT trajectories with structured tool slots and mixed invocation states. This stage activates the model's implicit tool representations and adaptive switching capability. (2) Self-regulated Reward-Driven Alignment. To address redundant tool usage caused by ambiguous cognitive boundaries, we first introduce the Net Tool Gain (NTG) metric to quantify this phenomenon. Based on this observation, we further propose a self-regulated reward mechanism. This mechanism penalizes ineffective tool dependency and encourages the model to perform knowledge routing, ensuring that implicit tools are invoked only when the model's internal knowledge is insufficient. BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks and achieving substantial gains in inference efficiency.
Binglin Ji, Anindya Sarkar, Hengchang Lu +2cs.LG cs.AI
In many scientific and engineering domains, maximizing discovery within a limited sampling budget demands strategic, observation-guided exploration. While generative models have enabled training-free reward alignment, current methods typically excel in local searches within narrow regions of the underlying distribution. These approaches struggle when preferences are unknown a priori and only revealed through sequential feedback-a scenario demanding broad exploration to uncover high-utility regions. To address this, we introduce Bootstrap Flow-Map-Tree (a.k.a BFMT), a novel computationally efficient sampling framework designed for history-aware global search and alignment under sampling budget constraints. BFMT enables full tree-path construction from any tree depth using a single function evaluation, drastically reducing computational overhead while providing critical foresight for sequential sampling. By enabling dynamic transition time steps scheduling, BFMT efficiently allocates its sampling budget, smoothly transitioning from broad global exploration to fine-grained local refinement of high-utility modes discovered through exploration. Extensive experiments and ablations across diverse search and alignment tasks demonstrate that BFMT substantially outperforms baseline approaches.
Binglin Ji, Anindya Sarkar, Hengchang Lu +2cs.LG cs.AI cs.CE
While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution. These approaches struggle when preferences are unknown a priori and only revealed through sequential feedback-a scenario demanding broad exploration to uncover high-utility regions. To address this, we propose Sequentially-Controlled Interactive Multi-Particle Flow-Maps (IMPFM), a framework for sample-efficient online feedback-driven search. IMPFM progressively transports a group of interactive particles toward the target distribution, maintaining the broad coverage essential for heterogeneous preference alignment. IMPFM introduces a principled and efficient posterior sample sharing mechanism across particles powered by flow maps. By correcting individual particle drift with the collective posterior samples of the entire ensemble at each resampling step, the framework maximizes sample utility to enable global exploration while actively mitigating reward over-optimization, typical of standard control frameworks. Paired with a principled exploration-exploitation reweighting mechanism involving multi-particle interaction, this sequentially corrected multi-particle dynamics explicitly preserves structural diversity and overcomes the weight degeneracy inherent to standard SMC samplers. Crucially, we prove that the resulting sampling framework yields a multi-particle interaction-aware Feynman-Kac corrector that progressively steers the multi-particle system toward a KL-tilted target distribution, facilitating global exploration and preventing mode collapse. Extensive empirical evaluations and rigorous ablations across diverse search and alignment tasks confirm the efficacy of IMPFM over existing baselines.
Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods. Existing density-approximated policy gradient methods rely on stochastic SDE samplers to construct tractable transition kernels, which introduce training-inference inconsistencies and necessitates Classifier-Free Guidance (CFG). While implicit frameworks such as DiffusionNFT directly optimize forward-process velocity fields, its heuristic fixed-magnitude corrections prevent optimization strength from relative intra-group quality. We propose \textit{Flow Advantage-Weighted Rectification} (\textbf{FlowAWR}), a paradigm that recasts continuous generative policy optimization as supervised regression toward a theoretically optimal velocity field. Starting from the optimal policy of a KL-constrained reward maximization, FlowAWR derives the optimal velocity field that admits a magnitude-aware, advantage-weighted rectification form, yielding SDE-free optimization and CFG-free generation. In comparative evaluations on SD3.5-Medium, FlowAWR achieves improved alignment performance alongside a 2$\times$ to 5$\times$ convergence acceleration over DiffusionNFT (e.g., reaching a 24.12 PickScore in 1.2k steps, versus 23.82 in 2.0k steps for DiffusionNFT and 23.50 in $>$4k steps for FlowGRPO). Under multi-reward constraints, FlowAWR sustains generation quality, satisfying structural rules while maintaining stable out-of-domain performance.
Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy. We identify a simple structural signature of this drift: across three post-training methods (NFT, AWM, DPO), RL fine-tuning inflates the per-step velocity norm $\|v_θ\|$ by $5\%$ to $15\%$ relative to the reference. A form of norm inflation has been studied in classifier-free guidance (CFG), where rescaling the velocity back to a reference norm at inference time can mitigate the resulting artifacts. However, this inference-time correction does not transfer cleanly to RL: rescaling $v_θ$ to match $\|v_{\text{ref}}\|$ at inference time neither improves reward nor fixes the quality degradation, because the inflation is co-adapted into the model weights. Furthermore, an adjoint sensitivity analysis shows that velocity magnitude rescaling carries no coherent first-order reward signal at the batch level, indicating that suppressing norm inflation is unlikely to remove a consistently reward-carrying component. Since inference-time renormalization fails while norm suppression carries no reward cost, training-time intervention is the appropriate strategy. Together, these findings motivate NormGuard, a hinge penalty that activates only when $\|v_θ\|$ exceeds $\|v_{\text{ref}}\|$ and composes additively with any velocity-local base loss. Across two base models, three post-training methods, and two reward proxies, NormGuard consistently improves MLLM-judged image quality and forensic realism while preserving reward, with gains that amplify under few-step inference and are not explained by early stopping.