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
1,295 results for “keyword:"distillation"” in ICLR 2027. 268 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SafetyTransfer: Distilling Harmful and Harmless Discrimination for Selective Refusal in Small Language Models▼4.3k2.00
[PDF]PP-CFG: Polarity-Preserving Guidance for Controllable Few-Step Image and Video Generation▲9.2k2.67
[PDF]CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing▼1.2k3.00
[PDF]Beyond Self-Consensus: Mitigating Self-Reinforcing Exploration Bias in Test-Time Reinforcement Learning▼4.3k2.00
[PDF]AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models▲3.8k2.50
[PDF]EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation▼14k2.00
[PDF]Beyond Static Criteria: Model–Rubric Co-Evolution for Reinforcement Learning with Self-Distillation▲5103.00
[PDF]Privileged Likelihood is not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation▲6.6k3.33
[PDF]ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving▲3942.67
[PDF]MUGAT-KD:A Multimodal-to-Unimodal Knowledge Distillation Framework for Pulmonary Nodule Malignancy Classification▼4.3k2.00
[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]AMID: Attribution Matching and Inverse-Network Distillation for Heterogeneous Super-Resolution▼4.5k2.67
[PDF]Guide the Tokens, Rank the Moments: Adaptive On-Policy Distillation for Temporal Video Grounding▲5.4k3.00
[PDF]REPRISE: Efficient Long-Context Diffusion Inference via Distillation through Reused KV Caches▲5.4k3.00
[PDF]The Perception-Override Reflex: When Speech Language Models Follow Perception Over Instructions▲6.1k2.00
[PDF]WMKD: Planning-Oriented World Model via Future-Guided Knowledge Distillation for End-to-End Autonomous Driving▲9.2k2.67
[PDF]Understanding the Benefits of Immature Teachers in Knowledge Distillation through Alignment and Regularization▼4.3k2.00
[PDF]E2M-Distill: Distilling End-to-End Driving Models into Motion-only Sim Agents for Large-Scale Autonomous Driving Simulation▲3942.67
Withdrawn or desk rejected (268)
[PDF]"The Whole Is Greater Than the Sum of Its Parts”: A Multi-Teacher CoT Distillation FrameworkDesk rejected
[PDF]Recoverable Coordination Distillation for Decentralized Multi-Agent Reinforcement LearningWithdrawn1.67
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]Collaborative Specialist Knowledge Distillation for Federated Offline Reinforcement LearningWithdrawn2.00