← Application Areas
Machine Learning › Application Areas ›

Model Merging

552 directly classified papers

Papers per year

Papers

MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer NIPS 2024
Mind’s Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models NAACL 2024
Chamain: Harmonizing Character Persona Integrity with Domain-Adaptive Knowledge in Dialogue Generation ACL 2024
When Quantization Affects Confidence of Large Language Models? NAACL 2024
Combining model-based controller and ML advice via convex reparameterization L4DC 2024
When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets? CONLL 2024
LM-Cocktail: Resilient Tuning of Language Models via Model Merging ACL 2024
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning NIPS 2024
MoExtend: Tuning New Experts for Modality and Task Extension ACL 2024
LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models EMNLP 2024
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction ACL 2024
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling NIPS 2024
Pruning Multilingual Large Language Models for Multilingual Inference EMNLP 2024
ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs EMNLP 2024
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment EMNLP 2024
SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models EMNLP 2024
To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models EMNLP 2024
MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning EMNLP 2024
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning NIPS 2024
Multi-Task Dense Prediction via Mixture of Low-Rank Experts CVPR 2024
Reusing Transferable Weight Increments for Low-resource Style Generation EMNLP 2024
How Far Can We Compress Instant-NGP-Based NeRF? CVPR 2024
MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic EMNLP 2024
DEM: Distribution Edited Model for Training with Mixed Data Distributions EMNLP 2024