← Application Areas
Machine Learning › Application Areas ›

Model Merging

552 directly classified papers

Papers per year

Papers

The Art of Saying No: Contextual Noncompliance in Language Models NIPS 2024
Compact Language Models via Pruning and Knowledge Distillation NIPS 2024
MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic EMNLP 2024
BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements WACV 2024
Reusing Transferable Weight Increments for Low-resource Style Generation EMNLP 2024
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning NIPS 2024
MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning EMNLP 2024
XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts ACL 2024
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks ACL 2024
Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks ACL 2024
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding ACL 2024
LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation ACL 2024
What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition EACL 2024
Emotion Arithmetic: Emotional Speech Synthesis via Weight Space Interpolation INTERSPEECH 2024
Model Composition for Multimodal Large Language Models ACL 2024
Learning or Self-aligning? Rethinking Instruction Fine-tuning ACL 2024
Domain-Agnostic Adapter Architecture for Deception Detection: Extensive Evaluations with the DIFrauD Benchmark COLING 2024
Fine-Tuning and Retrieval Augmented Generation for Question Answering Using Affordable Large Language Models COLING 2024
An Attribute Interpolation Method in Speech Synthesis by Model Merging INTERSPEECH 2024
SpaceByte: Towards Deleting Tokenization from Large Language Modeling NIPS 2024
Combining model-based controller and ML advice via convex reparameterization L4DC 2024
Low-Rank Adaptation for Multilingual Summarization: An Empirical Study NAACL 2024
ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks COLING 2024
Editing Language Model-Based Knowledge Graph Embeddings AAAI 2024
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation AAAI 2024