DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models

• URL: http://arxiv.org/abs/2608.09233v2
• Date: Thu, 13 Aug 2026 04:14:38 GMT
• Title: DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models
• Abstract summary: DreOPD is a Degraded-reference extrapolative OPD method for flow-matching models.<n>We show that DreOPD outperforms OPD and multi-task RL baselines in average performance.
• Score: 11.299607850340607
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-training, which may cause conflicts among task-specific optimization objectives. Reinforcement learning enables direct optimization of task-specific rewards beyond the original models, yet trajectory-level optimization may incur high-variance gradients and cross-task interference. On-policy distillation (OPD) offers dense and stable supervision on student rollouts, but conventional teacher matching remains imitation-based. We propose DreOPD, a Degraded-reference extrapolative OPD method for flow-matching models that bridges these two paradigms. Our DreOPD converts implicit reward extrapolation into closed-form velocity regression, enabling extrapolative post-training with the stability of OPD. It further uses a mildly degraded reference to strengthen the teacher-reference contrast, yielding a clearer extrapolation direction. Experiments on single- and multi-teacher settings show that DreOPD outperforms OPD and multi-task RL baselines in average performance, while surpassing specialized teachers on most metrics.

Related papers

• When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation [21.86522736658343]
  We propose Reward-Aligned On-Policy Distillation (RA-OPD) to mitigate misaligned teacher guidance.<n> RA-OPD selects more reliable trajectories to improve student model performance without requiring additional computational cost.<n>We evaluate RA-OPD on math and code benchmarks using models from the Qwen3 family and the DeepSeek-R1 family.
  arXiv  Detail & Related papers  (2026-08-28T06:05:50Z)
• Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher [36.07614733558147]
  We introduce textbfSelf-OPD, a teacher-free OPD framework for flow matching models.<n>Self-OPD branches the deterministic next-state prediction into $K$ SDE candidates, rolls them out with the ODE sampler, and compares their rewards against a deterministic self-reference baseline.<n>Experiments on single and mixed reward benchmarks show that Self-OPD outperforms prior RL and OPD methods without task-specific teachers.
  arXiv  Detail & Related papers  (2026-08-27T09:34:23Z)
• IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning [57.16513298507272]
  We propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR)<n>IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization.<n>For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional.
  arXiv  Detail & Related papers  (2026-08-11T08:20:02Z)
• D2PO: Optimizing Diffusion Samplers via Dynamic Preference [55.530862428116244]
  D2PO is a principled framework for optimizing diffusion sampling policies.<n>We introduce dynamic preferences, where the preferred samples used for alignment progressively improve.<n>Experiments demonstrate that D2PO aligns diffusion samplers with perceptual quality more faithfully.
  arXiv  Detail & Related papers  (2026-07-07T06:05:42Z)
• dOPSD: On-Policy Self-Distillation for Diffusion Language Models [52.60302464420127]
  Diffusion large language models generate text by iteratively denoising a masked sequence.<n>Supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards.<n>On-policy self-distillation (OPSD) offers a promising alternative, using one model as both student and teacher.
  arXiv  Detail & Related papers  (2026-07-05T17:47:29Z)
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models [55.01951088768769]
  DiffusionOPD is a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD)<n>We show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-05-14T16:49:09Z)
• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment [52.570581883709345]
  We propose Trajectory Matching Policy Balance Optimization (TMPO), which replaces reward with human-level reward distribution matching.<n>TMPO improves generative diversity over state-of-the-art methods by 9.1%, and achieves competitive performance in all downstream and efficiency metrics.<n>To further reduce multi-trajectory training time on large-scale flow- prefixes, TMPO incorporates Dynamic Tree Sampling models, where trajectories share denoising and branch at dynamically scheduled steps.
  arXiv  Detail & Related papers  (2026-05-09T04:41:02Z)
• Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback [28.40216934244641]
  Diffusion Denoising Ranking Optimization (Diffusion-DRO) is a new preference learning framework grounded in inverse reinforcement learning.<n>Diffusion-DRO removes the dependency on a reward model by casting preference learning as a ranking problem.<n>It integrates offline expert demonstrations with online policy-generated negative samples, enabling it to effectively capture human preferences.
  arXiv  Detail & Related papers  (2025-10-21T07:22:34Z)
• Prior-Guided Diffusion Planning for Offline Reinforcement Learning [5.819784482811376]
  Prior Guidance (PG) is a novel guided sampling framework that replaces the standard Gaussian prior of a behavior-cloned diffusion model.<n>We present an efficient training strategy that applies behavior regularization in latent space, and empirically demonstrate that PG outperforms state-the-art diffusion policies and planners across diverse long-horizon offline RL benchmarks.
  arXiv  Detail & Related papers  (2025-05-16T05:39:02Z)
• Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning [0.0]
  Fine-tuning foundation models via reinforcement learning (RL) has proven promising for aligning to downstream objectives. We exploit the hierarchical nature of diffusion models (DMs) and train them dynamically at each epoch with a tailored RL method. We show that models trained with HRF achieve better preservation of diversity in downstream tasks, thus enhancing the fine-tuning robustness and at uncompromising mean rewards.
  arXiv  Detail & Related papers  (2024-10-10T19:06:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.