English
Related papers

Related papers: On the Importance of Pretraining Data Alignment fo…

200 papers

Automated analyses of the outcome of a simulation have been an important part of atomistic modeling since the early days, addressing the need of linking the behavior of individual atoms and the collective properties that are usually the…

Chemical Physics · Physics 2019-05-22 Michele Ceriotti

Background: When using deep learning models, there are many possible vulnerabilities and some of the most worrying are the adversarial inputs, which can cause wrong decisions with minor perturbations. Therefore, it becomes necessary to…

Software Engineering · Computer Science 2024-01-12 Francisco Durán López , Silverio Martínez-Fernández , Michael Felderer , Xavier Franch

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Bo Zhao , Konda Reddy Mopuri , Hakan Bilen

As deep learning continues to be driven by ever-larger datasets, understanding which examples are most important for generalization has become a critical question. While progress in data selection continues, emerging applications require…

Machine Learning · Computer Science 2025-07-02 Mustafa Burak Gurbuz , Xingyu Zheng , Constantine Dovrolis

Machine learning has emerged as a new tool in chemistry to bypass expensive experiments or quantum-chemical calculations, for example, in high-throughput screening applications. However, many machine learning studies rely on small data…

Machine Learning · Computer Science 2024-10-15 Thorren Kirschbaum , Annika Bande

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

Computation and Language · Computer Science 2023-03-14 Anh Nguyen , Nikos Karampatziakis , Weizhu Chen

Every prediction is ultimately used in a downstream task. Consequently, evaluating prediction quality is more meaningful when considered in the context of its downstream use. Metrics based solely on predictive performance often diverge from…

Machine Learning · Computer Science 2025-08-26 Novin Shahroudi , Viacheslav Komisarenko , Meelis Kull

Property prediction on molecular graphs is an important application of Graph Neural Networks. Recently, unlabeled molecular data has become abundant, which facilitates the rapid development of self-supervised learning for GNNs in the…

Machine Learning · Computer Science 2023-10-31 Kha-Dinh Luong , Ambuj Singh

Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Lakshay Sharma , Alex Marin

State-of-the-art pretrained language models tend to perform below their capabilities when applied out-of-the-box on tasks that require understanding and working with numbers. Recent work suggests two main reasons for this: (1) popular…

Computation and Language · Computer Science 2023-06-12 Dominic Petrak , Nafise Sadat Moosavi , Iryna Gurevych

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

Machine Learning · Computer Science 2023-02-28 Shuo Yang , Zeke Xie , Hanyu Peng , Min Xu , Mingming Sun , Ping Li

Can AI systems trained on the scientific record up to a fixed point in time forecast the scientific advances that follow? Such a capability could help researchers identify collaborators and impactful research directions, and anticipate…

Machine learning interatomic potentials (MLIPs) balance high accuracy and lower costs compared to density functional theory calculations, but their performance often depends on the size and diversity of training datasets. Large datasets…

Machine Learning · Computer Science 2025-11-14 Benjamin Yu , Vincenzo Lordi , Daniel Schwalbe-Koda

Collecting annotated data for semantic segmentation is time-consuming and hard to scale up. In this paper, we for the first time propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Bowen Shi , Xiaopeng Zhang , Haohang Xu , Wenrui Dai , Junni Zou , Hongkai Xiong , Qi Tian

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Akshit Achara , Ram Krishna Pandey

Data-driven design of mechanical metamaterials is an increasingly popular method to combat costly physical simulations and immense, often intractable, geometrical design spaces. Using a precomputed dataset of unit cells, a multiscale…

Computational Engineering, Finance, and Science · Computer Science 2021-12-08 Yu-Chin Chan , Faez Ahmed , Liwei Wang , Wei Chen

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Zichao Li , Cihang Xie , Ekin Dogus Cubuk

The standard paradigm for training deep learning models on sensor data assumes that more data is always better. However, raw sensor streams are often imbalanced and contain significant redundancy, meaning that not all data points contribute…

Machine Learning · Computer Science 2025-12-15 Federico Pennino , Maurizio Gabbrielli

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…

Machine Learning · Computer Science 2026-05-21 Adam Ousherovitch , Ambuj Tewari

Traditional metrics like accuracy, F1-score, and precision are frequently used to evaluate machine learning models, however they may not be sufficient for evaluating performance on tiny, unbalanced, or high-dimensional datasets. A…

Machine Learning · Computer Science 2024-12-11 Serzhan Ossenov