On-Policy Distillation

Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-14

20 new papers

A weekly snapshot of new work published in On-Policy Distillation.

Period ending 2026-09-07

10 new papers

A weekly snapshot of new work published in On-Policy Distillation.

Inside this field

Focused directions

488 papers

Latest in On-Policy Distillation

Open your feed →
CardsList

  1. Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation

    Sep 15, 2026Shiqi Liu, Zeyu He, Letian Tao +9On-Policy Distillation

  2. A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients

    Sep 12, 2026Suwan Wu, Yumeng Lin, Pengcheng Yuan +1On-Policy DistillationKullback-Leibler Divergence

  3. KuaiRP Series Role-playing Models Technical Report

    Sep 12, 2026Yipeng Wang, Ziwei Zhang, Jiahui Zhang +2Role-PlayingLlm-Synthesized Code World Models

  4. Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models

    Sep 12, 2026Rui Zhu, Minglong Cao, Chenyu Zhou +2Future Llm-Assisted Solver DevelopmentUnsupervised On-Policy Self-Distillation

  5. SenseNova-U1.5: Towards Native Unified Visual Intelligence

    Sep 11, 2026Haiwen Diao, Jiahao Wang, Chenjing Ding +62Visual In-Context LearningOn-Policy Distillation

  6. Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identification

    Sep 11, 2026Menglin Wang, Xiaojin GongRe-IdentificationCross-Modality

  7. Negative Self-Distillation: Learning to Reason by Avoiding Flaws

    Sep 10, 2026Rongcan Pei, Zhepei Wei, Shuyao Xu +3Unsupervised On-Policy Self-DistillationSelf-Distillation

  8. Teacher Geometry Shapes Learnability in Teacher-Student Networks

    Sep 10, 2026Kai J. Sandbrink, Flavio Martinelli, Alexander van Meegen +2Teacher-Student Model PairsSingular Learning Theory

  9. On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data

    Sep 9, 2026Hongyuan Zhang, Xianda Guo, Yanlun Peng +6Vision-Language Model AdaptationOn-Policy Distillation

  10. CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shifts

    Sep 9, 2026Naibin Gu, Qingyi Si, Chenxu Yang +5On-Policy DistillationPolitical Compass Test

  11. Improving Cross-Lingual Token Representations by Adding a Pinch of SALT

    Sep 9, 2026Guillem RamírezCross-EncoderCross-Lingual Transfer

  12. Decision Shifts, Lost Label Functionality, and an Inconclusive Grounding Audit in Correctness-Gated Multi-Teacher Distillation

    Sep 9, 2026Xiaofei FengMulti-Teacher DistillationTeacher

  13. Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding

    Sep 8, 2026Zhenxin Qin, Peng Shi, Cong Han +3Video UnderstandingLong Video Understanding

  14. Learning Length-Extrapolatable Recurrent Models

    Sep 8, 2026Hanwen JiangRecurrent ModelEfficient Long-Context Inference

  15. Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

    Sep 8, 2026Youngrok Park, Sangmin Bae, Hojung Jung +6On-Policy DistillationMulti-Teacher Distillation

  16. Miles v0.1: Production-Level Post-Training

    Sep 8, 2026RadixArk, :, Tom Chen +11Reinforcement Learning Post-TrainingOn-Policy Distillation

  17. TV-Regulated OPD: Direction Matters in On-Policy Distillation

    Sep 8, 2026Han Xiao, Yifan Niu, Dongyi Liu +2On-Policy DistillationToken-Level Uncertainty

  18. Distillation as Probability Transport: Routed On-Policy Distillation

    Sep 8, 2026Tianle Xia, Lingxiang Hu, Yiding Sun +6On-Policy DistillationTeacher

  19. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

    Sep 8, 2026NeoHorse Team, Guoliang Cao, Guohao Dai +34Self-Improving AgentsReinforcement Learning Post-Training

  20. Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer

    Sep 7, 2026Zhiwei Ning, Zhen Zhou, Puhua Jiang +7Text-To-3D GenerationOn-Policy Distillation

  21. Extremely Sparse Supervision Incentivizes Reasoning Ability

    Sep 7, 2026Zhishuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu +2Token-Level SupervisionOn-Policy Distillation

  22. Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision

    Sep 3, 2026Shravan Venkatraman, Wenshuai Zhao, Mohammad Hassan Vali +1Multi-Object TrackingLong Video Understanding

  23. Rethinking On-Policy Distillation of Large Language Models II: One Training Example

    Sep 3, 2026Zixuan Fu, Bingxiang He, Yuxin Zuo +10On-Policy DistillationTraining Data

  24. Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR

    Sep 3, 2026Boyan Li, Bingsen Chen, Chenghao Yang +3Verifiable RewardsOn-Policy Distillation

  25. Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

    Sep 2, 2026Zhiwei Zhang, Zechen Sun, Fei Zhao +6On-Policy DistillationTeacher

  26. On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers

    Sep 1, 2026Vignesh Prabhakar, Jialing Pan, Anil Babu AnkisettipalliGenerative Reasoning Re-RankersOn-Policy Distillation

  27. Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall

    Sep 1, 2026Jacqueline He, Howard Yen, Shuyue Stella Li +9Heterogeneous Knowledge DistillationTeacher

  28. From Rollouts to Recipes: Self-Contained Post-Training for LLMs

    Sep 1, 2026Yifei Li, Lingling Zhang, Muye Huang +3Reinforcement Learning Post-TrainingUnsupervised On-Policy Self-Distillation

  29. When Tokenization is Secretly Output Supervision

    Sep 1, 2026Tanja Baeumel, Josef van Genabith, Simon OstermannToken-Level SupervisionNumerical Reasoning

  30. Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics

    Sep 1, 2026Samuel Young, César Jesús-Valls, Kazuhiro TeraoFoundation ModelNuclear Physics

  31. Hypotheses-Guided Self Distillation for Continual Personalization

    Aug 31, 2026EunJeong Hwang, Kushan Mitra, Dan Zhang +2PersonalizationPairwise Preferences

  32. Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

    Aug 31, 2026Yi Ding, Ruqi ZhangOn-Policy DistillationTeacher

  33. CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations

    Aug 31, 2026Gabriel Meseguer-Brocal, Yuexuan Kong, Romain HennequinJoint-Embedding Predictive ArchitecturesVideo Joint Embedding Predictive Architecture

  34. Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

    Aug 30, 2026Run Yang, Runpeng Dai, Jie Sun +5On-Policy DistillationTeacher

  35. Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher

    Aug 27, 2026Shiyi Zhang, Mushui Liu, Yunze Tong +8On-Policy DistillationFlow-Matching Loss

  36. Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding

    Aug 26, 2026Kaishen Wang, Dongdi Zhao, Yijun Liang +4Video UnderstandingUnsupervised On-Policy Self-Distillation

  37. Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

    Aug 17, 2026Ao Shen, Yongheng Zhang, Yinghui Li +3Latent Visual ReasoningLarge Multimodal Models

  38. Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation

    Aug 13, 2026Hmrishav Bandyopadhyay, Xuanchi Ren, Zijian Huang +7Autoregressive Video GenerationVideo Diffusion Models

  39. CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation

    Aug 13, 2026Enhan Li, Junhao He, Hongyang DuOn-Policy DistillationToken-Level Supervision

  40. HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models

    Aug 13, 2026Jiazi Bu, Pengyang Ling, Yujie Zhou +10Video Diffusion ModelsDiffusion Models

  41. Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents

    Aug 13, 2026Zechuan Wang, Siyuan Lu, Hongxuan Zhang +3Verifiable RewardsToken-Level Supervision

  42. Latent On-Policy Self-Distillation

    Aug 13, 2026Guibin Zhang, Jiayang Lyu, Ran Sun +4Unsupervised On-Policy Self-DistillationSelf-Teacher

  43. LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation

    Aug 12, 2026Zhixin Zhang, Xinke Jiang, Zhibang Yang +5Long-Horizon AgentsAgentic Reinforcement Learning

  44. Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling

    Aug 12, 2026Xinmu Ge, Zizhuo Zhang, Yu Huang +9On-Policy DistillationRp-Opsd

  45. REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation

    Aug 12, 2026Yang Sun, Lichao Ma, Houyuan Qin +5On-Policy DistillationOn-Policy

  46. Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing

    Aug 12, 2026Tianci Liu, Zihan Dong, Tianchun Li +8Multimodal Knowledge EditingUnsupervised On-Policy Self-Distillation

  47. Learning from Online User Feedback for Shopping Agents

    Aug 12, 2026Haobo Zhang, Kelong Mao, Sulong Xu +2Agentic CommerceNatural Language Feedback

  48. Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation

    Aug 11, 2026Shiyu Xuan, Zechao LiGraphical User InterfaceGraphical User Interface Agents

  49. ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation

    Aug 11, 2026Ximo Zhu, Ruiqi Liu, Rong Wang +8On-Policy DistillationRp-Opsd

  50. Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

    Aug 11, 2026Chris Han, Pengzhi Gao, Pei Fu +1Machine Translation QualityLarge Language Model Responses

  51. SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation

    Aug 11, 2026Zhou Liu, Ligang Huang, Zeli Su +5Action-Conditioned PredictionMultimodal Agents

  52. SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

    Aug 11, 2026HyeonJun Lee, Hyeonsik Jo, Jinwoo Chung +1Post-Training QuantizationHeterogeneous Knowledge Distillation

  53. DINO-A: Adapting Self-Distillation Vision Transformers to General Audio Representation Learning

    Aug 11, 2026Tomasz Radzikowski, Mateusz Modrzejewski, Przemysław RokitaSelf-Supervised Audio RepresentationsDino

  54. Mismatch Matters: On-Policy Distillation Beyond Token Agreement

    Aug 10, 2026Zichao Yu, Chengzhi Yu, Shengze Xu +4On-Policy DistillationTeacher-Student Model Pairs

  55. Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation

    Aug 10, 2026Yubo Jiang, Fengying Xie, Zhiguo Jiang +1Unsupervised On-Policy Self-DistillationUnsupervised Skill Discovery

  56. ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection

    Aug 10, 2026Jingtai He, Shiyuan Meng, Wenchao Meng +1Multimodal Industrial Anomaly DetectionGraph Anomaly Detection

  57. SR-OPSD: Self-Referenced On-Policy Self-Distillation

    Aug 10, 2026Zhuo Sun, Entong Li, Yanlong Zhao +7Unsupervised On-Policy Self-DistillationSelf-Teacher

  58. TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching

    Aug 10, 2026Chongjian Wang, Junjie GaoNon-Rigid Shape MatchingPoint Clouds

  59. Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents

    Aug 10, 2026Tianjun Pan, Yuan Li, Hongda Wang +8Unsupervised On-Policy Self-DistillationAgentic Reinforcement Learning

  60. WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training

    Aug 10, 2026Zehao Chen, Gongxun Li, Tianxiang Ai +9On-Policy DistillationRp-Opsd