English
Related papers

Related papers: Avoiding spurious sharpness minimization broadens …

200 papers

Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks. However, recent research has revealed that these models often rely on superficial features and shortcuts instead of developing…

Computation and Language · Computer Science 2025-02-26 Zihao Li , Ruixiang Tang , Lu Cheng , Shuaiqiang Wang , Dawei Yin , Mengnan Du

Training large language models (LLMs) typically relies on adaptive optimizers like Adam (Kingma & Ba, 2015) which store additional state information to accelerate convergence but incur significant memory overhead. Recent efforts, such as…

Machine Learning · Computer Science 2025-02-11 Meyer Scetbon , Chao Ma , Wenbo Gong , Edward Meeds

Curvature influences generalization, robustness, and how reliably neural networks respond to small input perturbations. Existing sharpness metrics are typically defined in parameter space (e.g., Hessian eigenvalues) and can be expensive,…

Machine Learning · Computer Science 2025-11-04 Jacob Poschl

The Segment Anything Model (SAM) has demonstrated strong performance in image segmentation of natural scene images. However, its effectiveness diminishes markedly when applied to specific scientific domains, such as Scanning Probe…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Yao Shen , Ziwei Wei , Chunmeng Liu , Shuming Wei , Qi Zhao , Kaiyang Zeng , Guangyao Li

Fine-tuning large language models (LLMs) with backpropagation achieves high performance but incurs substantial memory overhead, limiting scalability on resource-constrained hardware. Zeroth-order (ZO) optimization provides a…

Artificial Intelligence · Computer Science 2026-03-24 Shuo Wang , Ziyu Chen , Ming Tang

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions. In this paper, we focus on improving the robustness of a large class of learning algorithms that are formulated…

Machine Learning · Computer Science 2021-06-04 Quanming Yao , Hangsi Yang , En-Liang Hu , James Kwok

This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concerns become especially…

Artificial Intelligence · Computer Science 2025-11-26 Vishnu Asutosh Dasu , Md Rafi ur Rashid , Vipul Gupta , Saeid Tizpaz-Niari , Gang Tan

Real-world datasets often follow a long-tailed distribution, making generalization to tail classes difficult. Recent methods resorted to long-tail variants of Sharpness-Aware Minimization (SAM), such as ImbSAM and CC-SAM, to improve…

Machine Learning · Computer Science 2025-06-04 Sicong Li , Qianqian Xu , Zhiyong Yang , Zitai Wang , Linchao Zhang , Xiaochun Cao , Qingming Huang

We initiate a program of average smoothness analysis for efficiently learning real-valued functions on metric spaces. Rather than using the Lipschitz constant as the regularizer, we define a local slope at each point and gauge the function…

Statistics Theory · Mathematics 2020-11-10 Yair Ashlagi , Lee-Ad Gottlieb , Aryeh Kontorovich

Recent experiments have shown that, often, when training a neural network with gradient descent (GD) with a step size $\eta$, the operator norm of the Hessian of the loss grows until it approximately reaches $2/\eta$, after which it…

Machine Learning · Computer Science 2024-06-07 Philip M. Long , Peter L. Bartlett

We study sparse signal recovery from noisy linear observations using nonconvex log-sum regularization. The log-sum penalty reduces the shrinkage bias of $\ell_1$ regularization and more closely approximates the $\ell_0$ regularization, but…

Information Theory · Computer Science 2026-05-12 Keisuke Morita , Masayuki Ohzeki

Segment anything model (SAM) has demonstrated excellent generalizability in common vision scenarios, yet falling short of the ability to understand specialized data. Recently, several methods have combined parameter-efficient techniques…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yiran Song , Qianyu Zhou , Xuequan Lu , Zhiwen Shao , Lizhuang Ma

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Machine Learning · Computer Science 2022-10-26 Dongkyu Lee , Ka Chun Cheung , Nevin L. Zhang

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Hyung-Il Kim , Kimin Yun , Jun-Seok Yun , Yuseok Bae

While Vision-Language Models (VLMs) like CLIP have emerged as a dominant paradigm for generalizable deepfake detection, a representational disconnect remains: their semantic-centric pre-training is ill-suited for capturing non-semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Jipeng Liu , Haichao Shi , Siyu Xing , Rong Yin , Xiao-Yu Zhang

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Shumeng Li , Lei Qi , Qian Yu , Jing Huo , Yinghuan Shi , Yang Gao

This work introduces SAM-LLM, a novel hybrid architecture that bridges the gap between the contextual reasoning of Large Language Models (LLMs) and the physical precision of kinematic lane change models for autonomous driving. The system is…

Artificial Intelligence · Computer Science 2025-09-04 Zhuo Cao , Yunxiao Shi , Min Xu

We study a class of nonconvex nonsmooth optimization problems in which the objective is a sum of two functions: One function is the average of a large number of differentiable functions, while the other function is proper, lower…

Optimization and Control · Mathematics 2023-05-12 Duy-Nhat Phan , Sedi Bartz , Nilabja Guha , Hung M. Phan

Pruning provides a practical solution to reduce the resources required to run large language models (LLMs) to benefit from their effective capabilities as well as control their cost for training and inference. Research on LLM pruning often…

Computation and Language · Computer Science 2025-10-28 Yuanhe Tian , Junjie Liu , Xican Yang , Haishan Ye , Yan Song
‹ Prev 1 8 9 10 Next ›