Results 261 to 270 of about 2,403,325 (304)

HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

Neural Information Processing Systems
Adapting Large Language Models (LLMs) to new tasks through fine-tuning has been made more efficient by the introduction of Parameter-Efficient Fine-Tuning (PEFT) techniques, such as LoRA.
Chunlin Tian, Zhanying Shi, Zhijiang Guo, Li Li, Chengzhong Xu   +4 more
semanticscholar   +1 more source

Fine-tuning insulin therapy

Postgraduate Medicine, 1992
It is now possible to mimic normal insulin action more precisely than ever before with physiologic treatment programs using self-monitoring of blood glucose levels and newer insulins with more predictable action. Physiologic programs are more effective for both insulin-dependent (type I) and non-insulin-dependent (type II) diabetes mellitus.
openaire   +2 more sources

Fine-tuning triplification with Semion

2010
The Web of Data is fed mainly by "triplifiers (or RDFizers)", tools able to transform content (usually from databases) to linked data. Current triplifiers implement diverse methods, and are usually based on bulk recipes, which make fixed assumptions on the domain semantics.
NUZZOLESE, ANDREA GIOVANNI, Aldo Gangemi, CIANCARINI, PAOLO, PRESUTTI, VALENTINA   +3 more
openaire   +4 more sources

SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

AAAI Conference on Artificial Intelligence
Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have achieved superior performance and generalization capabilities, covered extensive areas of traditional tasks.
Yuze Zhao, Jintao Huang, Jinghan Hu, Xingjun Wang, Yunlin Mao, Daoze Zhang, Zeyinzi Jiang, Zhikai Wu, Baole Ai, Ang Wang, Wenmeng Zhou, Yingda Chen   +11 more
semanticscholar   +1 more source

ReFT: Reasoning with Reinforced Fine-Tuning

Annual Meeting of the Association for Computational Linguistics
One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations.
Trung Quoc Luong, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, Hang Li   +5 more
semanticscholar   +1 more source

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control

arXiv.org
Dynamical generative models that produce samples through an iterative process, such as Flow Matching and denoising diffusion models, have seen widespread use, but there have not been many theoretically-sound methods for improving these models with reward
Carles Domingo-Enrich, Michal Drozdzal, Brian Karrer, Ricky T. Q. Chen   +3 more
semanticscholar   +1 more source

FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations

Neural Information Processing Systems
The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning.
Ziyao Wang, Zheyu Shen, Yexiao He, Guoheng Sun, Hongyi Wang, Lingjuan Lyu, Ang Li   +6 more
semanticscholar   +1 more source

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Neural Information Processing Systems
Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios.
Yuexiang Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Shengbang Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, Sergey Levine   +10 more
semanticscholar   +1 more source

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

International Conference on Machine Learning
Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning ...
Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff G. Schneider, Tengyang Xie, S. Ermon, Chelsea Finn, Aviral Kumar   +8 more
semanticscholar   +1 more source

Editorial: CEACAM1: fine-tuned for fine-tuning

Journal of Leukocyte Biology, 2009
Zhangguo Chen, Lanfen Chen, Richard S Blumberg   +2 more
openaire   +1 more source