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
412 results for “keyword:"knowledge distillation"” in ICLR 2027. 81 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]On the Structure of Reinforcement Learning Policies: Recovery from Synthetic Observations via Geometric Coverage▲14k3.00
[PDF]BWB-KD: Domain Knowledge Distillation via Knowledge Injection, Reasoning Organization, and Activation▼5.8k2.33
[PDF]Teaching Lookup Tables to See in the Dark: Learning Complete Mappings from a Diffusion Teacher▼4.3k2.00
[PDF]When Clipping Reverses Correction: Failure Dynamics of Pointwise Forward-KL On-Policy Self-Distillation▲3.0k2.33
[PDF]Distill the Prior, Drop the Diffusion: Compact Feed-Forward Text Restoration from Diffusion Priors▼4.3k2.00
[PDF]KnowAcu: A Knowledge-Guided Heterogeneous Multi-Graph Learning Framework for Acupoint Prescription▼1.2k1.67
[PDF]Learn Only What Helps : Task-Prioritized Distillation from Heterogeneous Teachers for 2D Molecular Property Prediction▼5.8k2.33
[PDF]Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation▼1.2k1.67
[PDF]From Annual to In-Season: Uncertainty-Aware Distillation of Precomputed Geospatial Foundation Model Embeddings▲3952.67
[PDF]SELD: Selective On-Policy Distillation for Mathematical Reasoning via Semantic Error Localization▼4.3k2.75
[PDF]Cross-lingual Multi-view On-Policy Self-Distillation:Many Voices, One Model, No New Knowledge▼1.2k1.67
Withdrawn or desk rejected (81)
[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