English
Related papers

Related papers: Weight Updates as Activation Shifts: A Principled …

200 papers

Large pre-trained models (LPMs), such as large language models, have become ubiquitous and are employed in many applications. These models are often adapted to a desired domain or downstream task through a fine-tuning stage. This paper…

Machine Learning · Computer Science 2024-10-08 Juan Pablo Muñoz , Jinjie Yuan , Nilesh Jain

The effectiveness of single-model sequential recommendation architectures, while scalable, is often limited when catering to "power users" in sparse or niche domains. Our previous research, PinnerFormerLite, addressed this by using a fixed…

Machine Learning · Computer Science 2025-10-07 Akshay Mittal , Vinay Venkatesh , Krishna Kandi , Shalini Sudarshan

With the rise of language and multimodal models of ever-increasing size, pretraining a general-purpose foundational model and adapting it to downstream tasks has become common practice. To this end, adaptation efficiency can be a critical…

Machine Learning · Computer Science 2024-08-20 Yihe Dong

With the increasing number of parameters in large pre-trained models, LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. The LoRA method assumes that weight changes during fine-tuning…

Machine Learning · Computer Science 2024-08-07 Jihao Gu , Shuai Chen , Zelin Wang , Yibo Zhang , Ping Gong

Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and…

Computation and Language · Computer Science 2023-02-15 Xiaocong Yang , James Y. Huang , Wenxuan Zhou , Muhao Chen

The current leading computer vision models are typically feed forward neural models, in which the output of one computational block is passed to the next one sequentially. This is in sharp contrast to the organization of the primate visual…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Barak Battash , Lior Wolf

Despite growing interest in active inference for robotic control, its application to complex, long-horizon tasks remains untested. We address this gap by introducing a fully hierarchical active inference architecture for goal-directed…

Robotics · Computer Science 2025-07-24 Corrado Pezzato , Ozan Çatal , Toon Van de Maele , Riddhi J. Pitliya , Tim Verbelen

We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers. MetaTT enables flexible and parameter-efficient model adaptation by using a single shared TT to factorize transformer sub-modules. This…

Machine Learning · Computer Science 2025-11-18 Javier Lopez-Piqueres , Pranav Deshpande , Archan Ray , Mattia J. Villani , Marco Pistoia , Niraj Kumar

Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce…

Artificial Intelligence · Computer Science 2026-03-20 Zikang Ding , Qiying Hu , Yi Zhang , Hongji Li , Junchi Yao , Hongbo Liu , Lijie Hu

Fine-tuning is the primary mechanism for adapting foundation models to downstream tasks; however, standard approaches largely optimize task objectives in isolation and do not account for secondary yet critical alignment objectives (e.g.,…

Machine Learning · Computer Science 2026-02-06 Gaurav Bhatt , Aditya Chinchure , Jiawei Zhou , Leonid Sigal

LoRA has become a universal Parameter-Efficient Fine-Tuning (PEFT) technique that equips Large Language Models (LLMs) to adapt quickly to new tasks. However, when these models are scaled up, even the latest LoRA variants still introduce…

Computation and Language · Computer Science 2026-02-25 Xindian Ma , Rundong Kong , Peng Zhang , Ruoxiang Huang , Yongyu Jiang

Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprisingly complex as they depend on several hyperparameters such as…

Machine Learning · Computer Science 2026-02-09 Nan Chen , Soledad Villar , Soufiane Hayou

Inspired by biological neurons, the activation functions play an essential part in the learning process of any artificial neural network commonly used in many real-world problems. Various activation functions have been proposed in the…

Machine Learning · Computer Science 2022-12-29 Ameya D. Jagtap , George Em Karniadakis

Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full…

Cryptography and Security · Computer Science 2026-02-20 Sasha Behrouzi , Lichao Wu , Mohamadreza Rostami , Ahmad-Reza Sadeghi

Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Athmanarayanan Lakshmi Narayanan , Ranganath Krishnan , Amrutha Machireddy , Mahesh Subedar

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is…

Machine Learning · Computer Science 2021-04-14 Karim Huesmann , Luis Garcia Rodriguez , Lars Linsen , Benjamin Risse

The Parameter-Efficient Fine-Tuning (PEFT) method, which adjusts or introduces fewer trainable parameters to calibrate pre-trained models on downstream tasks, has become a recent research interest. However, existing PEFT methods within the…

Computation and Language · Computer Science 2023-12-13 Jiacheng Ruan , Jingsheng Gao , Mingye Xie , Suncheng Xiang , Zefang Yu , Ting Liu , Yuzhuo Fu

LoRA adapts large language models (LLMs) by restricting updates to low-rank subspaces of pre-trained weights. While this substantially reduces training cost, the effectiveness of adaptation critically depends on which subspace is chosen at…

Machine Learning · Computer Science 2026-05-28 Zhi-Quan Feng , Ying-Jia Lin , Hung-Yu Kao

A novel approach for structure alignment is presented, where the key ingredients are: (1) An error function formulation of the problem simultaneously in terms of binary (Potts) assignment variables and real-valued atomic coordinates. (2)…

Biological Physics · Physics 2007-05-23 M. Ohlsson , C. Peterson , M. Ringner , R. Blankenbecler

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian