Model Merging

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025 Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts ACL 2025 Diversity-Rewarded CFG Distillation ICLR 2025 Domain Adaptation of Foundation LLMs for e-Commerce ACL 2025 Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning CVPR 2025 DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic ICCV 2025 Dynamic Fisher-weighted Model Merging via Bayesian Optimization NAACL 2025 EdinHelsOW WMT 2025 CreoleMT System Description: Improving Lusophone Creole Translation through Data Augmentation, Model Merging and LLM Post-editing EMNLP 2025 Efficient Compositional Multi-tasking for On-device Large Language Models EMNLP 2025 Efficient Knowledge Deletion from Trained Models Through Layer-wise Partial Machine Unlearning JMLR 2025 Efficient Model Development through Fine-tuning Transfer EMNLP 2025 EmbedLLM: Learning Compact Representations of Large Language Models ICLR 2025 Encryption-Friendly LLM Architecture ICLR 2025 Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble Modeling ACL 2025 Ensembles of Low-Rank Expert Adapters ICLR 2025 Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing AAAI 2025 Exploiting Edited Large Language Models as General Scientific Optimizers NAACL 2025 Exploring Model Kinship for Merging Large Language Models EMNLP 2025 Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models EMNLP 2025 Findings of the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors ACL 2025 Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic ICLR 2025 FREE-Merging: Fourier Transform for Efficient Model Merging ICCV 2025 FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging EMNLP 2025 FuseChat: Knowledge Fusion of Chat Models EMNLP 2025 Fusing Highly Specialized Language Models for Comprehensive Expertise ACL 2025