Knowledge Distillation

Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging EACL 2026 Incoherence as Oracle-less Measure of Error in LLM-Based Code Generation AAAI 2026 Intention-Adaptive LLM Fine-Tuning for Text Revision Generation EACL 2026 KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation WACV 2026 KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation EACL 2026 Knowledge Cascade: Reverse Knowledge Distillation on Nonparametric Multivariate Functional Estimation JMLR 2026 L2-LoRA: Improving Low-Rank Adaptation with Layer-Specific Regularization AAAI 2026 Language Model Distillation: A Temporal Difference Imitation Learning Perspective AAAI 2026 LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval AAAI 2026 Leap of FAITH from GNN-to-MLP: Fairness Aware Inference via DisTillation of GrapH Knowledge AAAI 2026 Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations AAAI 2026 Learning Systems Expansion with Efficient Heterogeneity-aware Knowledge Transfer AAAI 2026 Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation AAAI 2026 LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models CVPR 2026 Listen like a Teacher: Mitigating Whisper Hallucinations Using Adaptive Layer Attention and Knowledge Distillation AAAI 2026 LLM-Oriented Token-Adaptive Knowledge Distillation AAAI 2026 LoKI: Low-Damage Knowledge Implanting of Large Language Models AAAI 2026 Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks AAAI 2026 MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM EACL 2026 MEDAL: multi-modal MEta-space Distillation and ALignment for Visual Compatibility Learning WACV 2026 MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge Through Group Direct Preference Optimization AAAI 2026 M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data AAAI 2026 Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization AAAI 2026 MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation AAAI 2026 MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings AAAI 2026