Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models

• URL: http://arxiv.org/abs/2608.04349v1
• Date: Wed, 05 Aug 2026 01:48:55 GMT
• Title: Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
• Abstract summary: Poly-OPD is a framework that can consolidate complementary strengths of heterogeneous teachers into a single compact flow-matching student.<n>Each student-generated image is re-encoded by a selected teacher's encoder and refined from a noise level matched by magnitude under the teacher's noise schedule.
• Score: 25.503555874738623
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Leading open text-to-image models often carry complementary strengths: one may lead on preference-aligned aesthetics while another follows compositional instructions more faithfully. However, differences in their autoencoders and noise schedules make it difficult to transfer these strengths across models. In this paper, we present Poly-OPD, a framework that can consolidate complementary strengths of heterogeneous teachers into a single compact flow-matching student. To bridge the incompatible latent spaces of different teachers, Poly-OPD performs on-policy distillation through a pixel bridge. Each student-generated image is re-encoded by a selected teacher's encoder and refined from a noise level matched by magnitude under the teacher's noise schedule. The resulting target is further matched to the student in frozen DINOv2 space, enabling supervision across incompatible latent spaces. To retain complementary capabilities without cross-teacher interference, Poly-OPD uses a gradient compatibility diagnostic to organize its adapters: attention LoRA modules are shared across teachers, whereas feed-forward adapters remain teacher-specific. During distillation, a gap-aware curriculum devotes more training to compositional categories where the student still falls short of the teacher. As each gap narrows, training shifts toward categories with larger remaining gaps. By distilling FLUX.1-dev and Z-Image into a 2.5B SD3.5-Medium student, Poly-OPD improves GenEval from 67.3 to 73.3, surpassing both larger teachers, and raises DrawBench HPSv3 from 9.34 to 11.35, consolidating both strengths within a switchable model.

Related papers

• STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models [14.682283642975271]
  We propose STEP-OPD, an on-policy distillation framework for image generation that extends the student's learning target beyond the teacher.<n>Instead of treating the teacher as the final target, we use the velocity difference between each task-specific teacher and the shared base model as a direction for further learning.<n>In addition, we align the direction and magnitude of representation changes between the student and teacher, enabling the student to learn how representations are progressively transformed.
  arXiv  Detail & Related papers  (2026-08-05T14:11:27Z)
• Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging [13.653084100002737]
  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.
  arXiv  Detail & Related papers  (2026-08-04T08:23:57Z)
• 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)
• Multi-Turn On-Policy Distillation with Prefix Replay [73.10000453999088]
  We propose Replayed-Prefix On-Policy Distillation (ReOPD) for agentic tasks.<n>ReOPD reuses pre-collected teacher trajectories as replayed prefixes.<n>It preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$times$ faster per training step than OPD.
  arXiv  Detail & Related papers  (2026-07-06T07:56:53Z)
• Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers [47.916191066149224]
  Bridge is a lightweight latent interface that maps Student latents into the Teacher space without modifying the Student backbone.<n>It improves SD 1.5 from 5.4 to 9.4 HPSv3 while preserving one-step inference, low latency, and broad ecosystem compatibility.
  arXiv  Detail & Related papers  (2026-06-30T17:51:26Z)
• Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients [89.89504265663057]
  Zone of Proximal Policy Optimization (ZPPO) is inspired by Vygotsky's zone of proximal development.<n>ZPPO pairs one correct teacher response with one incorrect student response as anonymized candidates the student must discriminate.<n>A prompt replay buffer recirculates each hard question until it either graduates-the student's mean rollout accuracy on it reaches half- or is FIFO-evicted.
  arXiv  Detail & Related papers  (2026-06-16T17:46:02Z)
• On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents [50.78688247330029]
  On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students.<n>We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout.<n>Guided-OPD improves Score by 21.1% and Success Rate by 25.5% over vanilla OPD on average.
  arXiv  Detail & Related papers  (2026-06-14T16:41:45Z)
• Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation [52.0297393822012]
  We introduce an assistant model as a bridge to facilitate smooth feature knowledge transfer between heterogeneous teachers and students.<n>Within our proposed design principle, the assistant model combines the advantages of cross-architecture inductive biases and module functions.<n>Our proposed method is evaluated across some homogeneous model pairs and arbitrary heterogeneous combinations of CNNs, ViTs, spatial KDs.
  arXiv  Detail & Related papers  (2024-10-16T08:02:49Z)
• Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation [31.460549289419923]
  Semi-supervised learning (SSL) techniques address the high labeling costs in 3D medical image segmentation. We introduce the Staged Selective Ensemble (SSE) module, which selects different ensemble methods based on the characteristics of the samples. Experimental results demonstrate the effectiveness of our proposed method in 3D medical image segmentation tasks.
  arXiv  Detail & Related papers  (2024-10-15T11:23:15Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)

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.