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113 results for “keyword:"on policy self distillation"” in ICLR 2027. 20 withdrawn or desk rejected listed apart.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]ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation▲5.4k3.00
[PDF]From Hesitation to Intuition: Internalizing Test-Time Adaptation into LLM Agents via On-Policy Self-Distillation▲3952.67
[PDF]The Solution Is the Supervision: Learning to Verify Reasoning without Human Step Labels▼5.8k2.33
[PDF]Reinforcing LLM Latent Reasoning with Contextual Loops through On-Policy Flow-Map Self-Distillation▼1.2k1.67
[PDF]Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes▲1.7k3.33
[PDF]On-Policy Self-Distillation with Outcome-Aligned Privileged Information for Agentic Reinforcement Learning▲9.2k2.67
[PDF]CV-OPSD: Self-Evolving Long-Context Reasoners via Zero-Annotation Clean-View On-Policy Self-Distillation▲14k3.00
[PDF]On-Policy Self Distillation As Automatisation: When and Why Thinking Collapses in Reasoning Models▼4.3k2.00
[PDF]When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing▲3.0k2.33
[PDF]ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models▼4.3k2.00
[PDF]Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models▲3952.67
[PDF]Learning from Decision Contrasts: History-Aligned Self-Distillation for Agentic Reinforcement Learning▲14k3.00
[PDF]Improving Safety Alignment and Health Safe Completion via Query-Specific Safety Rubrics in OPSD▲13k2.33
[PDF]X-OPSD: Culture-Preserving On-Policy Self-Distillation for Cross-Lingual Capability Transfer▼4.3k2.00
[PDF]Where to Apply Privilege: On-Policy Self-Distillation with Textual Privilege for Multimodal LLMs▼5.8k2.33
[PDF]From Evidence Orchestration to Reasoning Internalization for Radiology Report Generation▲9.2k2.67
Withdrawn or desk rejected (20)
[PDF]Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language ModelsDesk rejected
[PDF]ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use AgentsWithdrawn1.67
[PDF]Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented ReasoningDesk rejected2.67
[PDF]UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement LearningWithdrawn1.67
[PDF]PE-OPSD: Internalizing Prompt Enhancement into Flow-matching Models via On-Policy Self-DistillationWithdrawn2.00