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
595 results for “keyword:"on policy"” in ICLR 2027. 111 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing▲3.0k2.33
[PDF]Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?▼5.8k2.33
[PDF]Move Selection Upstream: Choosing What the Teacher Trains On in On-Policy Distillation▼1.2k1.67
[PDF]When Selective On-Policy Dstillation Rules Conflict: From Supervision Collapse to Minimal Repair▼1.2k1.67
[PDF]Improving Chain-of-Thought Monitorability in Large Language Models: Causal Bounds and Post-Training▲3.0k2.33
[PDF]Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging▲5.4k3.00
[PDF]Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics▲3.0k2.50
[PDF]ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models▼4.3k2.00
[PDF]Do As I Do, Not As I Say - On-Policy Distillation Inherits the Teacher in Vision-Language Models▲5.4k3.00
Withdrawn or desk rejected (111)
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33