NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
113 results for “keyword:"on policy self distillation"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation▼5.8k2.33
[PDF]CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing▼1.2k3.00
[PDF]HEIR: When the Student Inherits the Teacher's Seat Pareto-Competitive Reference Selection for On-Policy Self-Distillation of Reasoning LLMs▼5.3k1.33
[PDF]Retrospection Makes a Better Learner: Retrospective On-Policy Self-Distillation for Reasoning Models▲6.1k2.00
[PDF]Evidence-Aligned Multimodal On-Policy Self-Distillation for Fine-Grained Visual Understanding▼4.3k2.00
[PDF]CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation▲432.75
[PDF]Seeing What Matters: Visual-Selective On-Policy Self-Distillation for VLM Hallucination Mitigation▼1.2k3.00
[PDF]Beyond Output-Level Guidance: Leveraging Internal Exploration for LLM Self-Distillation▲5.4k3.00
[PDF]Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization▼4.3k2.00
[PDF]AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research▼1.2k1.67
[PDF]Collective Wisdom: On-Policy Self-Distillation with Synergistic Multi-Perspective Teacher Policy Fusion▲3.0k2.33
[PDF]When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation▲3.0k2.33
[PDF]Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation▲143.33
[PDF]GeoOPD: Internalizing Visual Search from Privileged Evidence for Remote Sensing Visual Reasoning▼5.8k2.33
[PDF]Distilling Structure, Not Solutions: Structural Bottlenecks for On-Policy Self-Distillation▼4.3k2.00
[PDF]RS-OPSD: Reliable Privileged On-Policy Self-Distillation For Ultra-High-Resolution Remote Sensing VQA▼1.2k3.00
[PDF]One Teacher, Many Tongues: Deficit-Aware Safety Distillation for Multilingual Alignment▲3.0k2.33
[PDF]Fair Credit Across Correct Modes: Mitigating Correct-Path Coverage Collapse in On-Policy Self-Distillation for Language Models▲9.2k2.67
[PDF]ROSA-IQA: Learning with Reasoning for Image Quality Assessment via On-Policy Self-Distillation▼4.3k2.00
[PDF]Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning Models▼1.3k1.75
Withdrawn or desk rejected (20)
[PDF]Learning to Access Multimodal Agent Memory: Agentic Retrieval with State-Level On-Policy Self-DistillationWithdrawn1.67
[PDF]Binding What to Where: Configurational Binding via On-Policy Self-Distillation for Multi-Object Spatial ReasoningWithdrawn1.67
[PDF]Paired On-Policy Self-Distillation for Situation-Dependent Persona Expression in Role-Playing ModelsWithdrawn
[PDF]Pixel-OPSD: Beyond Scalar Rewards for Pixel-Level MLLMs via On-Policy Self-DistillationWithdrawn2.00
[PDF]The Gravity of Privilege: Tilting Learning Measures in On-Policy Self-DistillationWithdrawn2.00