← Application Areas
Machine Learning › Application Areas ›

Model Merging

552 directly classified papers

Papers per year

Papers

Channel Merging: Preserving Specialization for Merged Experts AAAI 2025
Heterogeneous Federated Learning with Scalable Server Mixture-of-Experts IJCAI 2025
Temporal Information Retrieval via Time-Specifier Model Merging ACL 2025
DUT_IR at SemEval-2025 Task 11: Enhancing Multi-Label Emotion Classification with an Ensemble of Pre-trained Language Models and Large Language Models ACL 2025
MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors ACL 2025
Coling-UniA at SciVQA 2025: Few-Shot Example Retrieval and Confidence-Informed Ensembling for Multimodal Large Language Models ACL 2025
Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration AAAI 2025
Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing AAAI 2025
CITI: Enhancing Tool Utilizing Ability in Large Language Models Without Sacrificing General Performance AAAI 2025
UTF: Under-trained Tokens as Fingerprints —— a Novel Approach to LLM Identification ACL 2025
Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble Modeling ACL 2025
Superficial Self-Improved Reasoners Benefit from Model Merging EMNLP 2025
Controllable Style Arithmetic with Language Models ACL 2025
TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks ACL 2025
GeoEdit: Geometric Knowledge Editing for Large Language Models EMNLP 2025
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer ACL 2025
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling ACL 2025
A Pipeline to Assess Merging Methods via Behavior and Internals EMNLP 2025
Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval CVPR 2025
Robust Multi-Objective Preference Alignment with Online DPO AAAI 2025
StitchLLM: Serving LLMs, One Block at a Time ACL 2025
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging ACL 2025
Argus: A Compact and Versatile Foundation Model for Vision CVPR 2025
Representation Bending for Large Language Model Safety ACL 2025
LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025