Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Mind Lab, Song Cao, Vic Cao +59 authors
MinT is a managed infrastructure system that enables efficient low-rank adaptation training and serving by keeping base models resident and moving lightweight adapter revisions, scaling across multiple dimensions including large model architectures, reduced storage requirements, and distributed policy management.
Zhiyuan Liang, Dongwen Tang, Yuhao Zhou +11 authors
Drag-and-Drop LLMs generate task-specific parameters through prompt-conditioned parameter generation, achieving significant efficiency gains and cross-domain generalization without per-task training.
Vera Soboleva, Aibek Alanov, Andrey Kuznetsov +1 authors
T-LoRA, a timestep-dependent low-rank adaptation framework, enhances diffusion model personalization with a dynamic fine-tuning strategy and orthogonal initialization, improving concept fidelity and text alignment in data-limited settings.
David Bensaïd, Noam Rotstein, Roy Velich +2 authors
SingLoRA, a reformulated low-rank adaptation method, enhances parameter-efficient fine-tuning by learning a single low-rank matrix and its transpose, ensuring stable optimization and reducing parameter count.
Tianyu Fu, Yichen You, Zekai Chen +3 authors
Think-at-Hard (TaH) dynamically refines only hard tokens in LLMs using a neural decider and LoRA, improving reasoning performance with minimal additional parameters or iterations.
Sergey Pletenev, Maria Marina, Daniil Moskovskiy +4 authors
Low-rank adaptation (LoRA) effectively updates LLMs with new knowledge but risks degrading performance on external benchmarks due to data bias and overconfidence.
Dan Biderman, Jose Gonzalez Ortiz, Jacob Portes +9 authors
LoRA, a parameter-efficient finetuning method for large language models, underperforms full finetuning in target domains but provides better regularization and maintains diverse generation compared to other techniques.
Hakim Sidahmed, Samrat Phatale, Alex Hutcheson +16 authors
Parameter-efficient reinforcement learning using LoRA in RLHF matches conventional RLHF performance with reduced computational cost and memory usage.
Ting-Hsuan Chen, Jiewen Chan, Hau-Shiang Shiu +3 authors
A video editing framework combining deformation fields and diffusion priors produces high-quality canonical images for diverse video editing tasks with accelerated training using low-rank adaptation.
Jiale Kang, Ziyin Yue, Zheng Zhan +2 authors
Normalized Low-Rank Adaptation stabilizes LoRA training by normalizing down-projection matrices, accelerating convergence and improving performance without extra parameters or inference cost.
Ting Jiang, Shaohan Huang, Shengyue Luo +8 authors
MoRA, a high-rank updating method using square matrices, enhances the ability of large language models to learn and memorize new knowledge, especially in memory-intensive tasks, compared to LoRA.
Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti +15 authors
OpenVLA, a 7B-parameter open-source vision-language-action model, demonstrates strong performance in generalist manipulation and efficient fine-tuning for new tasks, outperforming larger closed models and from-scratch imitation learning methods.
Yuhui Xu, Lingxi Xie, Xiaotao Gu +6 authors
QA-LoRA algorithm reduces computational requirements for large language models by quantizing weights during fine-tuning and integrating auxiliary weights post-training.
Yiming Wang, Yu Lin, Xiaodong Zeng +1 authors
MultiLoRA improves multi-task adaptation for large language models by reducing the dominance of top singular vectors in LoRA parameter updates through horizontal scaling and modified initialization.
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram +9 authors
jina-embeddings-v3, a large-scale text embedding model, achieves state-of-the-art performance in multilingual and long-context retrieval tasks using Low-Rank Adaptation and Matryoshka Representation Learning.
Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki Markus Asano
Vector-based Random Matrix Adaptation (VeRA) reduces the number of trainable parameters by 10x compared to LoRA while maintaining performance, and is demonstrated on benchmarks like GLUE and E2E, showing its utility in instruction-following.
Arnav Chavan, Zhuang Liu, Deepak Gupta +2 authors
GLoRA, an advanced method for parameter-efficient fine-tuning, enhances LoRA with a generalized prompt module and modular layer-wise structure search, offering superior performance across diverse tasks with fewer parameters and computational costs.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号