Results 141 to 150 of about 173,284 (257)

Evolutionarily divergent DUF4465 domains have a common vitamin B12‐binding function

FEBS Open Bio, EarlyView.
We show that DUF4465 family proteins, widespread across bacteria from gut microbiomes, hydrothermal vents, and soil, share a common vitamin B12‐binding function. These augmented β‐jellyroll proteins bind vitamin B12 via extended loops. Our findings establish sequence‐diverse DUF4465 proteins as a widespread class of B12‐binding proteins, highlighting ...
Charlea Clarke, Michal Banasik, Rokas Juodeikis, Martin J. Warren, Richard W. Pickersgill   +4 more
wiley   +1 more source

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as model sizes grow.
Yaras, Can, Wang, Peng, Balzano, Laura, Qu, Qing   +3 more
core  

Low-Rank RNN Adaptation for Context-Aware Language Modeling

, 2018
Thesis (Ph.D.)--University of Washington, 2018A long-standing weakness of statistical language models is that their performance drastically degrades if they are used on data that varies even slightly from the data on which they were trained. In practice,
Jaech, Aaron
core  

MemLoTrack: Enhancing TIR Anti-UAV Tracking with Memory-Integrated Low-Rank Adaptation. [PDF]

Sensors (Basel)
Park JK, Han JH.
europepmc   +1 more source

Systemic dysregulation of apolipoproteins in amyotrophic lateral sclerosis serum

FEBS Open Bio, EarlyView.
Amyotrophic lateral sclerosis (ALS) is a fatal disease that damages motor neurons. This study found that people with ALS show significant changes in blood fats and the proteins that carry them. Several apolipoproteins were higher, lipid balances were altered, and normal protein–lipid relationships were disrupted.
Finula I. Isik, Russell Pickford, Hannah C. Timmins, Olivier Piguet, Glenda M. Halliday, Matthew C. Kiernan, Woojin Scott Kim   +6 more
wiley   +1 more source

ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models

Parameter-efficient fine-tuning (PEFT) is widely studied for its effectiveness and efficiency in the era of large language models. Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular and representative method.
Zhu, Wei, Liu, Zequan, Lyn, Jiawen, Tian, Xing, Graham, Yvette   +4 more
core  

A personalized communication efficient federated learning framework with low rank adaptation for intelligent leukemia diagnosis. [PDF]

Sci Rep
Suresh P, Keerthika P, Kumar ARN.
europepmc   +1 more source

Large‐scale bidirectional arrayed genetic screens identify OXR1 and EMC4 as modifiers of αSynuclein aggregation

FEBS Open Bio, EarlyView.
Activation of the mitochondrial protein OXR1 increases pSyn129 αSynuclein aggregation by lowering ATP levels and altering mitochondrial membrane potential, particularly in response to MSA‐derived fibrils. In contrast, ablation of the ER protein EMC4 enhances autophagic flux and lysosomal clearance, broadly reducing α‐synuclein aggregates.
Sandesh Neupane, Lea Nikolić, Lorenzo Maraio, Thomas Goiran, Nathan Karpilovsky, Stefano Sellitto, Vangelis Bouris, Jiang‐An Yin, Ronald Melki, Edward A Fon, Adriano Aguzzi, Elena De Cecco   +11 more
wiley   +1 more source

Fast Randomized Low-Rank Adaptation of Pre-trained Language Models with PAC Regularization

Low-rank adaptation (LoRA) achieves parameter efficient fine-tuning for large language models (LLMs) by decomposing the model weight update into a pair of low-rank projection matrices. Yet, the memory overhead restricts it to scale up when the model size
Qian, Dong,, Lei, Zijian,, Cheung, William K.,   +2 more
core  

Study on salient object segmentation based on depth information guidance and SAM low-rank adaptation fine-tuning. [PDF]

PLoS One
M A W.
europepmc   +1 more source