knowledge distillation

Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data AAAI 2024 Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging NeurIPS 2024 UDON: Universal Dynamic Online distillatioN for generic image representations NeurIPS 2024 UEGP: Unified Expert-Guided Pre-training for Knowledge Rekindle NAACL 2024 Uncertainty-Guided Never-Ending Learning to Drive CVPR 2024 Understanding the Gains from Repeated Self-Distillation NeurIPS 2024 Understanding the Role of the Projector in Knowledge Distillation AAAI 2024 Ungeneralizable Examples CVPR 2024 UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling ICLR 2024 UniADS: Universal Architecture-Distiller Search for Distillation Gap AAAI 2024 Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling NeurIPS 2024 Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE NeurIPS 2024 UniPTS: A Unified Framework for Proficient Post-Training Sparsity CVPR 2024 UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition ICLR 2024 Unlocking Pre-trained Image Backbones for Semantic Image Synthesis CVPR 2024 Unlocking the Potential of Global Human Expertise NeurIPS 2024 Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding ACL 2024 Unsupervised Human Preference Learning EMNLP 2024 Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training CVPR 2024 Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization EMNLP 2024 Unveiling the Magic: Investigating Attention Distillation in Retrieval-Augmented Generation NAACL 2024 Using Early Readouts To Mediate Featural Bias in Distillation WACV 2024 Variational Distillation of Diffusion Policies into Mixture of Experts NeurIPS 2024 Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy Interspeech 2024 VE-KD: Vocabulary-Expansion Knowledge-Distillation for Training Smaller Domain-Specific Language Models EMNLP 2024