Model Merging

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models ICLR 2024 Model Composition for Multimodal Large Language Models ACL 2024 Model Fusion through Bayesian Optimization in Language Model Fine-Tuning NeurIPS 2024 Modeling linking between text and lexicon with OntoLex-Lemon: a case study of computational terminology for the Babylonian Talmud COLING 2024 Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024 Model Merging by Uncertainty-Based Gradient Matching ICLR 2024 MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning EMNLP 2024 MoExtend: Tuning New Experts for Modality and Task Extension ACL 2024 MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer NeurIPS 2024 Multi-Task Dense Prediction via Mixture of Low-Rank Experts CVPR 2024 MUSCLE: A Model Update Strategy for Compatible LLM Evolution EMNLP 2024 Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation ICLR 2024 On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL NAACL 2024 Orthogonal Adaptation for Modular Customization of Diffusion Models CVPR 2024 ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks COLING 2024 Parameter Competition Balancing for Model Merging NeurIPS 2024 Parameter-Efficient Multi-Task Model Fusion with Partial Linearization ICLR 2024 PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models NAACL 2024 Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning NeurIPS 2024 Post-Hoc Reversal: Are We Selecting Models Prematurely? NeurIPS 2024 PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation EACL 2024 Pruning Multilingual Large Language Models for Multilingual Inference EMNLP 2024 RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models ACL 2024 ReFACT: Updating Text-to-Image Models by Editing the Text Encoder NAACL 2024 Reusing Transferable Weight Increments for Low-resource Style Generation EMNLP 2024