English
Related papers

Related papers: Foundation Model's Embedded Representations May De…

200 papers

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…

Machine Learning · Computer Science 2021-04-27 Francisco Utrera , Evan Kravitz , N. Benjamin Erichson , Rajiv Khanna , Michael W. Mahoney

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Artificial Intelligence · Computer Science 2025-06-03 Yifan Hao , Xingyuan Pan , Hanning Zhang , Chenlu Ye , Rui Pan , Tong Zhang

The human brain can effectively learn a new task from a small number of samples, which indicate that the brain can transfer its prior knowledge to solve tasks in different domains. This function is analogous to transfer learning (TL) in the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-06 Satoshi Nishida , Yusuke Nakano , Antoine Blanc , Naoya Maeda , Masataka Kado , Shinji Nishimoto

Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing…

Machine Learning · Computer Science 2025-08-11 Jiahao Chen , Bin Qin , Jiangmeng Li , Hao Chen , Bing Su

We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model with some trait T (such as liking owls or being misaligned)…

Machine Learning · Computer Science 2025-07-22 Alex Cloud , Minh Le , James Chua , Jan Betley , Anna Sztyber-Betley , Jacob Hilton , Samuel Marks , Owain Evans

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To…

Machine Learning · Computer Science 2023-03-09 William Merrill , Vivek Ramanujan , Yoav Goldberg , Roy Schwartz , Noah Smith

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

Computation and Language · Computer Science 2025-12-01 Sumit Mamtani , Abhijeet Bhure

This work addresses fair generative models. Dataset biases have been a major cause of unfairness in deep generative models. Previous work had proposed to augment large, biased datasets with small, unbiased reference datasets. Under this…

Machine Learning · Computer Science 2022-12-05 Christopher TH Teo , Milad Abdollahzadeh , Ngai-Man Cheung

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised…

Machine Learning · Computer Science 2020-07-03 Yu Sun , Xiaolong Wang , Zhuang Liu , John Miller , Alexei A. Efros , Moritz Hardt

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its training distribution using quantities available prior to test-time evaluation. Building on the…

The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within. A biased model can then make decisions that disproportionately harm certain groups in society. Much…

Machine Learning · Computer Science 2022-06-28 José Pombal , Pedro Saleiro , Mário A. T. Figueiredo , Pedro Bizarro

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world…

Machine Learning · Computer Science 2019-09-27 Hong Liu , Mingsheng Long , Jianmin Wang , Michael I. Jordan

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

Computation and Language · Computer Science 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen

The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the robustness to distribution shift from the algorithmic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Ziquan Liu , Yi Xu , Yuanhong Xu , Qi Qian , Hao Li , Rong Jin , Xiangyang Ji , Antoni B. Chan

Public pretraining is a promising approach to improve differentially private model training. However, recent work has noted that many positive research results studying this paradigm only consider in-distribution tasks, and may not apply to…

Machine Learning · Computer Science 2025-09-10 Pratiksha Thaker , Amrith Setlur , Zhiwei Steven Wu , Virginia Smith

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…

Machine Learning · Computer Science 2019-01-15 Wouter M. Kouw , Marco Loog

Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the training distribution where the observed distribution…

Machine Learning · Statistics 2019-05-29 Matias Vera , Pablo Piantanida , Leonardo Rey Vega

Deep tabular modelling increasingly relies on in-context learning where, during inference, a model receives a set of $(x,y)$ pairs as context and predicts labels for new inputs without weight updates. We challenge the prevailing view that…

Machine Learning · Computer Science 2025-11-14 Junwei Ma , Nour Shaheen , Alex Labach , Amine Mhedhbi , Frank Hutter , Anthony L. Caterini , Valentin Thomas

Transformers have the capacity to act as supervised learning algorithms: by properly encoding a set of labeled training ("in-context") examples and an unlabeled test example into an input sequence of vectors of the same dimension, the…

Machine Learning · Computer Science 2024-12-16 Spencer Frei , Gal Vardi
‹ Prev 1 4 5 6 7 8 10 Next ›