Knowledge Distillation

Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective EMNLP 2024 How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models EMNLP 2024 HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning NeurIPS 2024 ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer ACL 2024 iKUN: Speak to Trackers without Retraining CVPR 2024 Image Understanding Makes for A Good Tokenizer for Image Generation NeurIPS 2024 Impartial Adversarial Distillation: Addressing Biased Data-Free Knowledge Distillation via Adaptive Constrained Optimization AAAI 2024 Implanting LLM’s Knowledge via Reading Comprehension Tree for Toxicity Detection ACL 2024 Improved Distribution Matching Distillation for Fast Image Synthesis NeurIPS 2024 Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation EMNLP 2024 Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation NeurIPS 2024 Incremental pre-training from smaller language models ACL 2024 INDUS: Effective and Efficient Language Models for Scientific Applications EMNLP 2024 InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries ACML 2024 Investigating Mysteries of CoT-Augmented Distillation EMNLP 2024 IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation CVPR 2024 KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning ACL 2024 Knowledge Composition using Task Vectors with Learned Anisotropic Scaling NeurIPS 2024 Knowledge Distillation from Monolingual to Multilingual Models for Intelligent and Interpretable Multilingual Emotion Detection ACL 2024 Knowledge Editing in Language Models via Adapted Direct Preference Optimization EMNLP 2024 KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis NeurIPS 2024 Label Attentive Distillation for GNN-Based Graph Classification AAAI 2024 LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations NeurIPS 2024 Language-Informed Visual Concept Learning ICLR 2024 Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic ACL 2024