Knowledge Distillation

D3still: Decoupled Differential Distillation for Asymmetric Image Retrieval CVPR 2024 D^4: Dataset Distillation via Disentangled Diffusion Model CVPR 2024 Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition AAAI 2024 Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance AAAI 2024 DB-LLM: Accurate Dual-Binarization for Efficient LLMs ACL 2024 DDK: Distilling Domain Knowledge for Efficient Large Language Models NeurIPS 2024 DDViT: Double-Level Fusion Domain Adapter Vision Transformer (Student Abstract) AAAI 2024 De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts CVPR 2024 DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models EMNLP 2024 Decoupled Kullback-Leibler Divergence Loss NeurIPS 2024 Deep Classifier Mimicry without Data Access AISTATS 2024 DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets CVPR 2024 Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models NeurIPS 2024 Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation NeurIPS 2024 DiConStruct: Causal Concept-based Explanations through Black-Box Distillation CLeaR 2024 Differentially Private Knowledge Distillation via Synthetic Text Generation ACL 2024 DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation NAACL 2024 DimA: A Parameter-efficient Fine-tuning Method with Knowledge Transfer Based on Transformer COLING 2024 DIMSIM: Distilled Multilingual Critics for Indic Text Simplification ACL 2024 DIOD: Self-Distillation Meets Object Discovery CVPR 2024 DisCEdit: Model Editing by Identifying Discriminative Components NeurIPS 2024 Discrepancy and Uncertainty Aware Denoising Knowledge Distillation for Zero-Shot Cross-Lingual Named Entity Recognition AAAI 2024 Distillation Enhanced Generative Retrieval ACL 2024 Distillation with Explanations from Large Language Models COLING 2024 Distilled Datamodel with Reverse Gradient Matching CVPR 2024