teacher model

ASKD: Reinforcement Learning-Style Knowledge Distillation with Quality-Adaptive Skewness AAAI 2026 LLM-Oriented Token-Adaptive Knowledge Distillation AAAI 2026 Pareto-Based Heterogeneous Knowledge Distillation for MLPs on Graphs AAAI 2026 Stratos: An End-to-End Distillation Pipeline for Customized LLMs Under Distributed Cloud Environments AAAI 2026 Active Large Language Model-Based Knowledge Distillation for Session-Based Recommendation AAAI 2025 Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation ACL 2025 Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias AAAI 2025 Comparative Knowledge Distillation WACV 2025 Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models EMNLP 2025 From Teacher to Student: Tracking Memorization Through Model Distillation ACL 2025 GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost ICLR 2025 Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles Interspeech 2025 Knowledge Distillation with Refined Logits ICCV 2025 MiniPLM: Knowledge Distillation for Pre-training Language Models ICLR 2025 Quantifying Knowledge Distillation using Partial Information Decomposition AISTATS 2025 Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation ICML 2025 SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models NAACL 2025 Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales EMNLP 2025 Towards the Law of Capacity Gap in Distilling Language Models ACL 2025 What to Distill? Fast Knowledge Distillation with Adaptive Sampling ICCV 2025 Adversarial Moment-Matching Distillation of Large Language Models NeurIPS 2024 DFD: Distilling the Feature Disparity Differently for Detectors ICML 2024 Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation ICML 2024 Ex2Eg-MAE: A Framework for Adaptation of Exocentric Video Masked Autoencoders for Egocentric Social Role Understanding ECCV 2024 FreeKD: Knowledge Distillation via Semantic Frequency Prompt CVPR 2024