Knowledge Distillation

Hybrid Distillation from RBMT and NMT: Helsinki-NLP’s Submission to the Shared Task on Translation into Low-Resource Languages of Spain EMNLP 2024 HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning NeurIPS 2024 HYDRA: Model Factorization Framework for Black-Box LLM Personalization NeurIPS 2024 Hypernetwork-Assisted Parameter-Efficient Fine-Tuning with Meta-Knowledge Distillation for Domain Knowledge Disentanglement NAACL 2024 Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis NeurIPS 2024 HYPERTTS: Parameter Efficient Adaptation in Text to Speech Using Hypernetworks COLING 2024 ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer ACL 2024 IDC: Boost Text-to-image Retrieval via Indirect and Direct Connections COLING 2024 Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval ICLR 2024 Impartial Adversarial Distillation: Addressing Biased Data-Free Knowledge Distillation via Adaptive Constrained Optimization AAAI 2024 Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model NAACL 2024 Improved Distribution Matching Distillation for Fast Image Synthesis NeurIPS 2024 Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation EMNLP 2024 Improving Audio Classification with Low-Sampled Microphone Input: An Empirical Study Using Model Self-Distillation Interspeech 2024 Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model Interspeech 2024 Improving Continual Few-shot Relation Extraction through Relational Knowledge Distillation and Prototype Augmentation COLING 2024 Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment ACL 2024 Improving Personalized Sentiment Representation with Knowledge-enhanced and Parameter-efficient Layer Normalization COLING 2024 Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement CVPR 2024 Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation CVPR 2024 Incremental pre-training from smaller language models ACL 2024 Incremental Sequence Labeling: A Tale of Two Shifts ACL 2024 Induced Model Matching: Restricted Models Help Train Full-Featured Models NeurIPS 2024 INDUS: Effective and Efficient Language Models for Scientific Applications EMNLP 2024 Initializing Models with Larger Ones ICLR 2024