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
925 results for “keyword:"knowledge"” in ICLR 2027. 207 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Clean Data, Dirty Secrets: Backdoor Transfer in LLM Distillation via Defect Amplification▼4.3k2.00
[PDF]ComplexLogicalQA: Benchmarking Knowledge Graph Question Answering Beyond Chain-like Reasoning▼4.3k2.00
[PDF]Efficient Zero-shot Spatio-Temporal Forecasting via Multi-scale Expert Distilled Mixed Hashing Attention▼4.3k2.00
[PDF]RepairChemist: Cross-Language Repair Skill Distillation for Low-Resource Program Repair▲5103.00
[PDF]Balancing Specialists with Safety: Lagrangian Anchored Multi-Teacher On-Policy Distillation for Large Language Models▼1361.33
[PDF]RUR-Edit: Instance-Aware Residual Allocation and Utility-Aware Update Reconstruction for Knowledge Editing▼4.3k2.00
[PDF]SILTA: Reference Learning and Target Adaptation for Spatial Transcriptomic Deconvolution▼4.3k2.00
[PDF]BEAD: Blind-spot Entity-aware Advantage Distillation for Cooperative Multi-Agent Reinforcement Learning▲3952.67
[PDF]Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation▼1.3k1.75
[PDF]ManiEdit: Sequential Unstructured Knowledge Editing for Language Models from a Manifold Perspective
[PDF]The Role of Local Background Knowledge in Maximally Oriented Partially Directed Acyclic Graphs▲5103.00
Withdrawn or desk rejected (207)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]Beyond the Observed: Knowledge-Informed Controllable Augmentation for Few-Shot Class-Incremental LearningWithdrawn1.50