English
Related papers

Related papers: Lyra: An Efficient and Expressive Subquadratic Arc…

200 papers

Transformer models are computationally costly on long sequences since regular attention has quadratic $O(n^2)$ time complexity. We introduce Wavelet-Enhanced Random Spectral Attention (WERSA), a novel mechanism of linear $O(n)$ time…

Machine Learning · Computer Science 2025-07-14 Vincenzo Dentamaro

Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local…

Machine Learning · Computer Science 2024-10-31 Zhan Zhuang , Xiequn Wang , Yulong Zhang , Wei Li , Yu Zhang , Ying Wei

The characterization of dynamical processes in living systems provides important clues for their mechanistic interpretation and link to biological functions. Thanks to recent advances in microscopy techniques, it is now possible to…

Data Analysis, Statistics and Probability · Physics 2023-11-29 Jesús Pineda , Benjamin Midtvedt , Harshith Bachimanchi , Sergio Noé , Daniel Midtvedt , Giovanni Volpe , Carlo Manzo

Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by treating all update directions with equal importance, and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Xi Xiao , Chenrui Ma , Yunbei Zhang , Chen Liu , Zhuxuanzi Wang , Yanshu Li , Lin Zhao , Guosheng Hu , Tianyang Wang , Hao Xu

Driven by the continuous development of models such as Multi-Layer Perceptron, Convolutional Neural Network (CNN), and Transformer, deep learning has made breakthrough progress in fields such as computer vision and natural language…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Shuang Liu , Lina Zhao , Tian Wang , Huaqing Wang

Composed of amino acid chains that influence how they fold and thus dictating their function and features, proteins are a class of macromolecules that play a central role in major biological processes and are required for the structure,…

Quantitative Methods · Quantitative Biology 2022-07-15 Aaron Wang

Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the weight change, i.e.,…

Machine Learning · Computer Science 2024-05-07 Ziqi Gao , Qichao Wang , Aochuan Chen , Zijing Liu , Bingzhe Wu , Liang Chen , Jia Li

The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated…

Computation and Language · Computer Science 2024-11-26 Kerim Büyükakyüz

Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary strong-vs-weak decisions and couple learned parameters to specific model identities,…

Computation and Language · Computer Science 2026-05-19 Aashna Garg , Siddharth Singha Roy , Jinu Jang , Federico Brancasi , Shengyu Fu

The approximation capability of ANNs and their RNN instantiations, is strongly correlated with the number of parameters packed into these networks. However, the complexity barrier for human understanding, is arguably related to the number…

Neural and Evolutionary Computing · Computer Science 2023-03-10 Julian Lemmel , Radu Grosu

Parsimonious representations are ubiquitous in modeling and processing information. Motivated by the recent Multi-Layer Convolutional Sparse Coding (ML-CSC) model, we herein generalize the traditional Basis Pursuit problem to a multi-layer…

Machine Learning · Computer Science 2018-11-22 Jeremias Sulam , Aviad Aberdam , Amir Beck , Michael Elad

LoRA-based continual learning represents a promising avenue for leveraging pre-trained models in downstream continual learning tasks. Recent studies have shown that orthogonal LoRA tuning effectively mitigates forgetting. However, this work…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Shimou Ling , Liang Zhang , Jiangwei Zhao , Lili Pan , Hongliang Li

Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. LoRA saves memory by training only low rank perturbations to selected weight matrices. In this work, we compare the performance of…

Foundation models are reshaping computational pathology by enabling transfer learning, where models pre-trained on vast datasets can be adapted for downstream diagnostic, prognostic, and therapeutic response tasks. Despite these advances,…

Deploying Scientific Machine Learning surrogates in industrial CFD workflows requires adapting pretrained models to new vehicle families without large datasets; yet whether geometric representations learned by a geometry encoder transfer to…

Computational Engineering, Finance, and Science · Computer Science 2026-05-29 Seunghwan Keum , Alok Warey

Accurate prediction of RNA properties, such as stability and interactions, is crucial for advancing our understanding of biological processes and developing RNA-based therapeutics. RNA structures can be represented as 1D sequences, 2D…

Quantitative Methods · Quantitative Biology 2025-04-22 Junjie Xu , Artem Moskalev , Tommaso Mansi , Mangal Prakash , Rui Liao

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), but it still incurs notable overhead and suffers from parameter interference in complex datasets. While recent…

Computation and Language · Computer Science 2025-12-19 Chunlin Tian , Xuyang Wei , Huanrong Liu , Zhijiang Guo , Li Li

Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effective. Inspired by an effort to investigate the different roles…

Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks,…

Machine Learning · Computer Science 2025-10-23 Zhi Zhang , Yixian Shen , Congfeng Cao , Ekaterina Shutova

In continual learning (CL), catastrophic forgetting often arises due to feature drift. This challenge is particularly prominent in the exemplar-free continual learning (EFCL) setting, where samples from previous tasks cannot be retained,…

Machine Learning · Computer Science 2025-04-01 Xuan Liu , Xiaobin Chang
‹ Prev 1 8 9 10 Next ›