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
436 results for “keyword:"on policy distill"” in ICLR 2027. 71 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Rewarding the Graph Behind the Chain: Topology-Aware Process Supervision for RL and Reasoning Distillation▲3952.67
[PDF]Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation▼4.5k2.25
[PDF]Swift MOPD: A Better Balanced Method for Parameter and Data Allocation in Multi Teacher On Policy Distillation▼4.3k2.00
[PDF]DSpark-OPD: Acceptance-Aligned On-Policy Distillation for Semi-Autoregressive Speculative Drafting▼1.2k1.67
[PDF]Every Fork Has a Price: The Precision–Coverage Trade-off in On-Policy Distillation of Reasoning Models▼1.2k1.67
[PDF]When to Trust Your Teacher: Uncertainty-Aware On-Policy Distillation for Embodied Policies▼4.3k2.00
[PDF]The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation▼5.8k2.33
[PDF]Schedule the Optimizer, Not the Teacher: Diagnosing and Mitigating Long-Horizon Collapse in On-Policy Self-Distillation▲3.0k2.33
[PDF]Discover and Internalize: A Continual Co-Evolving Training Loop for Self-Improvement Agents▼1.2k1.67
[PDF]DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models▲5103.00
[PDF]Conflux: Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation▼1.2k3.00
[PDF]Think Before You Link: On-Policy Distillation Enhanced Graph Reasoning for Multimodal Knowledge Graph Completion▼4.3k2.00
Withdrawn or desk rejected (71)
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM DistillationDesk rejected1.50
[PDF]Ask the Memory, Not the Teacher: Episode-Swap Gating Prevents Stale-Memory Hallucination in On-Policy Distillation of Agent MemoryDesk rejected2.33