Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

• URL: http://arxiv.org/abs/2608.03316v1
• Date: Tue, 04 Aug 2026 08:23:57 GMT
• Title: Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
• Abstract summary: On-policy distillation in which a teacher corrects samples that the student itself generates presupposes that the two models speak the same language.<n>We present Any-OPD, to our knowledge the first framework for on-policy distillation between arbitrary pairs of latent flow-matching generators.
• Score: 13.653084100002737
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher latents cannot serve as targets in a foreign coordinate system, per-pixel losses against a teacher that stochastically re-draws local detail degenerate into blur or divergence, and timestep indices lose their meaning across mismatched schedules. We present Any-OPD, to our knowledge the first framework for on-policy distillation between arbitrary pairs of latent flow-matching generators. Any-OPD treats the teacher purely as a black-box sampler and connects the two models at exactly one point: a frozen, model-agnostic vision representation in which their independently decoded outputs are compared, sidestepping every assumption about latents, features, or architecture. Trajectory correspondence is recovered by matching continuous noise levels instead of step indices, and a brief anchoring phase, in which teacher samples are re-encoded through the student's own VAE, ensures the on-policy gradient measures sample quality rather than domain mismatch. Distilling the 12B FLUX.1-dev into the 2.5B SD3.5-Medium, Any-OPD lifts the student's PickScore from 0.846 to 0.884 and HPSv3 from 9.12 to 10.97, rivaling the teacher at a fifth of its size, where direct latent regression fails to train at all.

Related papers

• CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning [3.2847672479922783]
  We propose a class-wise reliability-Aware Distillation (CRAD) for federated learning.<n>CRAD weights each teacher by its per-class reliability (precision, or inverse variance)<n>It consistently outperforms competing methods in global accuracy.
  arXiv  Detail & Related papers  (2026-08-31T22:36:30Z)
• 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)
• WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training [48.290951447286744]
  WDL-OPD is a mixture-constrained co-training method with two trainable policies.<n>An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a geometric mixture of their token distributions is matched to a frozen teacher by reverse KL.<n>We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.
  arXiv  Detail & Related papers  (2026-08-10T11:22:53Z)
• Weak-to-Strong On-Policy Distillation [21.651421588571296]
  We introduce Weak-to-Strong On-Policy Distillation (W2S-OPD), a framework that improves the strong student by distilling from multiple weak models.<n>Across four math and three code benchmarks, W2S-OPD outperforms OPD, enables the student to surpass the domain teacher, and keeps improving the student even when every supervision source is weaker.
  arXiv  Detail & Related papers  (2026-07-28T20:31:48Z)
• OPOD: On-Policy Omni Distillation [55.440058537827134]
  Training a single model on pooled multimodal data often fails to match models specialized for individual modalities.<n>We present On-Policy Omni Distillation (OPD), which routes each student response to the matching text, image, or audio teacher.<n>OPD achieves the best average score at every scale, reaching 70.8, 51.7, and 46.2.
  arXiv  Detail & Related papers  (2026-07-23T04:55:04Z)
• A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms [0.0]
  Few-step distilled diffusion students cut text-to-image inference from 50 to 1-8 network evaluations.<n>We replace the scalar with a decomposable probe that injects controlled perturbations along three layers.<n>We report a bootstrap-median Bures W22 selectivity ratio on Inception features.
  arXiv  Detail & Related papers  (2026-07-03T12:18:24Z)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment [7.13416637929041]
  Diffusion and continuous-flow generative models achieve high-quality generation.<n>Reflow-based distillation simplifies teacher ODE trajectories so that a student model can approximate the teacher transport with fewer steps.<n>We introduce a marginal-alignment regularizer that penalizes the discrepancy between the student-induced marginal and the corresponding teacher marginal at the endpoint of each distillation interval.
  arXiv  Detail & Related papers  (2026-06-28T09:19:44Z)
• SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling [22.832360652920332]
  On-policy distillation (OPD) trains a student on its own trajectories with dense per-token supervision from a stronger teacher.<n>We propose Sign-Gated On-Policy Distillation (SG-OPD), which uses a binary verifier as a trust signal for the teacher.<n> Experiments on competition-level mathematical reasoning benchmarks show that SG-OPD consistently outperforms standard OPD.
  arXiv  Detail & Related papers  (2026-06-08T10:11:58Z)
• When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning [45.79647925282674]
  On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher.<n>Existing entropy-based OPD methods relax this uniformity by modulating token-level supervision with teacher entropy.<n>We propose Position-Weighted On-Policy Self-Distillation (PW-OPSD), which applies an increasing position weight while keeping the same student rollout, privileged teacher pass, and clipped forward-KL target as OPSD.
  arXiv  Detail & Related papers  (2026-05-20T18:14:03Z)
• AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals [65.71225905458182]
  Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher.<n>This setup provides dense token-level feedback without relying on a separate external model.<n>We introduce AVSD, a novel method of self-distillation with multiple privileged-information views.
  arXiv  Detail & Related papers  (2026-05-20T03:06:36Z)
• DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation [49.98710755440242]
  Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities.<n>We reveal a critical inefficiency in this approach: up to 69% of the prompts in standard chart / document reasoning datasets are effectively zero-delta.<n>We propose a staged synthesis pipeline that repurposes existing datasets as seeds, actively targeting student failure modes to produce better prompts.
  arXiv  Detail & Related papers  (2026-05-15T02:04:12Z)
• Improved Distribution Matching Distillation for Fast Image Synthesis [54.72356560597428]
  We introduce DMD2, a set of techniques that lift this limitation and improve DMD training. First, we eliminate the regression loss and the need for expensive dataset construction. Second, we integrate a GAN loss into the distillation procedure, discriminating between generated samples and real images.
  arXiv  Detail & Related papers  (2024-05-23T17:59:49Z)

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.