English
Related papers

Related papers: The Devil is in the Detail: Simple Tricks Improve …

200 papers

Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities. When domain distribution changes, the vulnerability of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Wenlong Yu , Dongyue Chen , Qilong Wang , Qinghua Hu

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained base model to get…

Computer Vision and Pattern Recognition · Computer Science 2020-06-03 Liang Song , Jinlu Liu , Yongqiang Qin

Symbolic Regression remains an NP-Hard problem, with extensive research focusing on AI models for this task. Transformer models have shown promise in Symbolic Regression, but performance suffers with smaller datasets. We propose applying…

Machine Learning · Computer Science 2025-07-01 Kaustubh Kislay , Shlok Singh , Soham Joshi , Rohan Dutta , Jay Shim , George Flint , Kevin Zhu

Transformers, central to the successes in modern Natural Language Processing, often falter on arithmetic tasks despite their vast capabilities --which paradoxically include remarkable coding abilities. We observe that a crucial challenge is…

Computation and Language · Computer Science 2023-11-28 Ruoqi Shen , Sébastien Bubeck , Ronen Eldan , Yin Tat Lee , Yuanzhi Li , Yi Zhang

Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-29 Yunhan Zhao , Ye Tian , Charless Fowlkes , Wei Shen , Alan Yuille

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learning, transformers are…

Machine Learning · Computer Science 2021-12-13 Luana Ruiz , Joshua Ainslie , Santiago Ontañón

Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit…

Machine Learning · Computer Science 2026-05-19 Zhaiming Shen , Alex Havrilla , Rongjie Lai , Alexander Cloninger , Wenjing Liao

Recent advances in image-based saliency prediction are approaching gold standard performance levels on existing benchmarks. Despite this success, we show that predicting fixations across multiple saliency datasets remains challenging due to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Matthias Kümmerer , Harneet Singh Khanuja , Matthias Bethge

We analyze the grounded SCAN (gSCAN) benchmark, which was recently proposed to study systematic generalization for grounded language understanding. First, we study which aspects of the original benchmark can be solved by commonly used…

Computation and Language · Computer Science 2021-09-28 Linlu Qiu , Hexiang Hu , Bowen Zhang , Peter Shaw , Fei Sha

Performance optimization is an increasingly challenging but often repetitive task. While each platform has its quirks, the underlying code transformations rely on data movement and computational characteristics that recur across…

Software Engineering · Computer Science 2023-03-16 Lukas Trümper , Tal Ben-Nun , Philipp Schaad , Alexandru Calotoiu , Torsten Hoefler

Monocular depth estimation has been widely studied, and significant improvements in performance have been recently reported. However, most previous works are evaluated on a few benchmark datasets, such as KITTI datasets, and none of the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Jinwoo Bae , Kyumin Hwang , Sunghoon Im

The strength of machine learning models stems from their ability to learn complex function approximations from data; however, this strength also makes training deep neural networks challenging. Notably, the complex models tend to memorize…

Computer Vision and Pattern Recognition · Computer Science 2023-04-17 Mofassir ul Islam Arif , Mohsan Jameel , Josif Grabocka , Lars Schmidt-Thieme

Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance…

Machine Learning · Statistics 2026-05-27 Gyeonghun Kang , Changwoo J. Lee , Xiang Cheng

Distributed learning facilitates the scaling-up of data processing by distributing the computational burden over several nodes. Despite the vast interest in distributed learning, generalization performance of such approaches is not well…

Machine Learning · Statistics 2020-05-05 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

We study the approximation capabilities, convergence speeds and on-convergence behaviors of transformers trained on in-context recall tasks -- which requires to recognize the \emph{positional} association between a pair of tokens from…

Machine Learning · Computer Science 2025-10-22 Quan Nguyen , Thanh Nguyen-Tang

Neural networks have revolutionized language modeling and excelled in various downstream tasks. However, the extent to which these models achieve compositional generalization comparable to human cognitive abilities remains a topic of…

Computation and Language · Computer Science 2023-10-19 Osman Batur İnce , Tanin Zeraati , Semih Yagcioglu , Yadollah Yaghoobzadeh , Erkut Erdem , Aykut Erdem