Self-Supervised Visual On-Policy Distillation

• URL: http://arxiv.org/abs/2608.14144v1
• Date: Fri, 14 Aug 2026 09:52:01 GMT
• Title: Self-Supervised Visual On-Policy Distillation
• Abstract summary: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry.<n>We introduce Self-Supervised Visual On-Policy Distillation (S$2$VOPD)<n>S$2$VOPD distills the teacher's distribution conditioned on the original image on-policy into the student distribution conditioned on a strongly augmented view of the same image.
• Score: 63.83705343579541
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest. This raises a fundamental question: where can informative asymmetry come from when nothing privileged is available? We answer this by inverting where the asymmetry comes from. Rather than adding privileged information to the teacher, we subtract information from the student. This asymmetry creates the same effective learning signal for free as a teacher with access to information unavailable to the student, without ground-truth annotations, rewards, or a separate stronger teacher model. Building on this principle, we introduce Self-Supervised Visual On-Policy Distillation (S$^2$VOPD), a simple yet effective method that constructs on-policy learning signals from asymmetric augmented views. S$^2$VOPD distills the teacher's distribution conditioned on the original image on-policy into the student distribution conditioned on a strongly augmented view of the same image. We systematically explore a broad design space of visual augmentations and uncover that (1) asymmetry matters: all four augmentation families improve performance, while symmetric self-distillation degrades it; (2) strength matters: performance peaks at a moderate strength; and (3) the gap must remain task-consistent: augmentations that completely remove the question-relevant evidence can induce large but uninformative discrepancies. Across six fine-grained perception benchmarks, S$^2$VOPD improves Qwen3.5-4B from 70.7% to 77.4%, above all open-source models compared, up to Qwen3-VL at 235B, and surpasses GPT-5.4. While holding training data the same, it recovers 96% of the improvement achieved by methods with privileged information. Website is at https://williamium3000.github.io/s2vopd

Related papers

• One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation [3.0867286767516937]
  On-policy distillation trains a language model on its own generations while a teacher scores them token by token.<n>The teacher is the model itself, conditioned on privileged information the student will not have at test time.<n>Early results were promising, with accuracy comparable to reinforcement learning at a fraction of the generated tokens.<n>But the same asymmetry that produces the signal also biases it.
  arXiv  Detail & Related papers  (2026-08-26T15:52:19Z)
• 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)
• Visual Contrastive Self-Distillation [61.298159957622886]
  We propose Visual Contrastive Self-Distillation, which converts image-content removal into an on-policy self-distillation signal.<n>We use this contrast to sharpen the teacher's original-image distribution within its plausible support, and distill the resulting full-distribution target into the student.
  arXiv  Detail & Related papers  (2026-07-23T17:37:37Z)
• DemoPSD: Disagreement-Modulated Policy Self-Distillation [49.30809363804017]
  On-policy self-distillation has emerged as a practical method for training large language models.<n>DemoPSD steers the student toward a weighted geometric combination of the teacher and student distributions.
  arXiv  Detail & Related papers  (2026-07-02T17:58:29Z)
• DOPD: Dual On-policy Distillation [59.65986569617147]
  On-policy distillation offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals.<n>We propose DOPD, an advantage-aware dual distillation paradigm that dynamically routes token-level supervision between privileged teacher and privileged student policies.<n>Experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that DOPD consistently outperforms Vanilla OPD.
  arXiv  Detail & Related papers  (2026-06-29T17:55:53Z)
• 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)
• SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies [87.78260740602674]
  Generalization has been a long-standing challenge for reinforcement learning (RL) In this work, we consider robust policy learning which targets zero-shot generalization to unseen visual environments with large distributional shift. We propose SECANT, a novel self-expert cloning technique that leverages image augmentation in two stages to decouple robust representation learning from policy optimization.
  arXiv  Detail & Related papers  (2021-06-17T17:28:18Z)

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.