English
Related papers

Related papers: Specialization after Generalization: Towards Under…

200 papers

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…

Machine Learning · Computer Science 2025-11-11 Zeman Li , Ali Behrouz , Yuan Deng , Peilin Zhong , Praneeth Kacham , Mahdi Karami , Meisam Razaviyayn , Vahab Mirrokni

Post-training has demonstrated its importance in enhancing the reasoning capabilities of large language models (LLMs). The primary post-training methods can be categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning…

Machine Learning · Computer Science 2025-10-21 Mingyang Liu , Gabriele Farina , Asuman Ozdaglar

Conventional DNN training paradigms typically rely on one training set and one validation set, obtained by partitioning an annotated dataset used for training, namely gross training set, in a certain way. The training set is used for…

Neural and Evolutionary Computing · Computer Science 2020-07-03 Boyu Zhang , A. K. Qin , Hong Pan , Timos Sellis

Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples…

Machine Learning · Computer Science 2019-02-11 Amir Erfan Eshratifar , Mohammad Saeed Abrishami , David Eigen , Massoud Pedram

Training a deep neural network with a small amount of data is a challenging problem as it is vulnerable to overfitting. However, one of the practical difficulties that we often face is to collect many samples. Transfer learning is a…

Machine Learning · Computer Science 2020-07-13 Yunho Jeon , Yongseok Choi , Jaesun Park , Subin Yi , Dongyeon Cho , Jiwon Kim

Foundation models are large-scale machine learning models that are pre-trained on massive amounts of data and can be adapted for various downstream tasks. They have been extensively applied to tasks in Natural Language Processing and…

Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approach controls for task familiarity by giving each model…

Machine Learning · Computer Science 2026-03-16 Kun Wang , Reinhard Heckel

Despite the impressive advancements achieved using deep-learning for functional brain activity analysis, the heterogeneity of functional patterns and scarcity of imaging data still pose challenges in tasks such as prediction of future onset…

Image and Video Processing · Electrical Eng. & Systems 2023-12-25 Wenhui Cui , Haleh Akrami , Ganning Zhao , Anand A. Joshi , Richard M. Leahy

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we learn an optimal model in training data, it could have better generalization performance in testing tasks. However, learning such a…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Penghao Jiang , Xin Ke , ZiFeng Wang , Chunxi Li

Scaling laws motivate the development of Time Series Foundation Models (TSFMs) that pre-train vast parameters and achieve remarkable zero-shot forecasting performance. Surprisingly, even after fine-tuning, TSFMs cannot consistently…

Machine Learning · Computer Science 2025-12-23 Lifan Zhao , Yanyan Shen , Zhaoyang Liu , Xue Wang , Jiaji Deng

Deep learning time-series models are often used to make forecasts that inform downstream decisions. Since these decisions can differ from those in the training set, there is an implicit requirement that time-series models will generalize…

Machine Learning · Computer Science 2024-11-04 Thomas Crasson , Yacine Nabet , Mathias Lécuyer

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of…

Computation and Language · Computer Science 2020-08-12 Lifu Tu , Garima Lalwani , Spandana Gella , He He

As machine learning (ML) algorithms are increasingly used in high-stakes applications, concerns have arisen that they may be biased against certain social groups. Although many approaches have been proposed to make ML models fair, they…

Machine Learning · Computer Science 2023-02-01 Thai-Hoang Pham , Xueru Zhang , Ping Zhang

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

Computation and Language · Computer Science 2024-10-18 Shuyang Jiang , Yusheng Liao , Ya Zhang , Yanfeng Wang , Yu Wang

To develop a preliminary understanding towards Graph Foundation Models, we study the extent to which pretrained Graph Neural Networks can be applied across datasets, an effort requiring to be agnostic to dataset-specific features and their…

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…

Computer Vision and Pattern Recognition · Computer Science 2022-08-05 Amogh Joshi , Dario Guevara , Mason Earles

Large language models are versatile tools but are not suitable for small inference budgets. Small models have more efficient inference, but their lower capacity means that their performance can be good only if one limits their scope to a…

Machine Learning · Computer Science 2024-11-01 David Grangier , Angelos Katharopoulos , Pierre Ablin , Awni Hannun

Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We study test-time adaptation of foundation models for few-shot…

Machine Learning · Statistics 2026-02-04 Tahir Qasim Syed , Behraj Khan

This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation of source training and target testing, but exploit the…

Machine Learning · Computer Science 2024-07-02 Sameer Ambekar , Zehao Xiao , Jiayi Shen , Xiantong Zhen , Cees G. M. Snoek

The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Paul Gavrikov , Janis Keuper