English
Related papers

Related papers: Scaling Laws for Task-Optimized Models of the Prim…

200 papers

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…

Machine Learning · Statistics 2026-02-05 Kazuto Fukuchi , Ryuichiro Hataya , Kota Matsui

This paper asks whether current self-supervised learning methods, if sufficiently scaled up, would be able to reach human-level visual object recognition capabilities with the same type and amount of visual experience humans learn from.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 A. Emin Orhan

Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faster training at the expense of a drop in accuracy. Conversely,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Elvis Nunez , Thomas Merth , Anish Prabhu , Mehrdad Farajtabar , Mohammad Rastegari , Sachin Mehta , Maxwell Horton

We study empirical scaling laws for transfer learning between distributions in an unsupervised, fine-tuning setting. When we train increasingly large neural networks from-scratch on a fixed-size dataset, they eventually become data-limited…

Machine Learning · Computer Science 2021-02-03 Danny Hernandez , Jared Kaplan , Tom Henighan , Sam McCandlish

Many deep architectures and self-supervised pre-training techniques have been proposed for human activity recognition (HAR) from wearable multimodal sensors. Scaling laws have the potential to help move towards more principled design by…

Machine Learning · Computer Science 2025-05-22 Tom Hoddes , Alex Bijamov , Saket Joshi , Daniel Roggen , Ali Etemad , Robert Harle , David Racz

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

Machine Learning · Computer Science 2025-07-16 Zhengyu Chen , Siqi Wang , Teng Xiao , Yudong Wang , Shiqi Chen , Xunliang Cai , Junxian He , Jingang Wang

Empirically, large-scale deep learning models often satisfy a neural scaling law: the test error of the trained model improves polynomially as the model size and data size grow. However, conventional wisdom suggests the test error consists…

Machine Learning · Computer Science 2025-06-11 Licong Lin , Jingfeng Wu , Sham M. Kakade , Peter L. Bartlett , Jason D. Lee

Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise "precision-aware" scaling laws for both training and inference. We propose…

Convolutional Neural Networks have dramatically improved in recent years, surpassing human accuracy on certain problems and performance exceeding that of traditional computer vision algorithms. While the compute pattern in itself is…

Computer Vision and Pattern Recognition · Computer Science 2018-07-10 Michaela Blott , Thomas B. Preusser , Nicholas Fraser , Giulio Gambardella , Kenneth OBrien , Yaman Umuroglu , Miriam Leeser

Deep convolutional neural networks trained for image object categorization have shown remarkable similarities with representations found across the primate ventral visual stream. Yet, artificial and biological networks still exhibit…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Alex Hernández-García , Peter König , Tim C. Kietzmann

Deep neural networks (DNNs) once showed increasing alignment with primate perception and neural responses as they improved on vision benchmarks, raising hopes that advances in AI would yield better models of biological vision. However, we…

Neurons and Cognition · Quantitative Biology 2025-04-29 Drew Linsley , Pinyuan Feng , Thomas Serre

Vision Transformers (ViTs) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant…

Machine Learning · Computer Science 2026-02-25 Huy Trinh , Rebecca Ma , Zeqi Yu , Tahsin Reza

Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…

Artificial Intelligence · Computer Science 2025-09-30 Xinyi Wang , Shawn Tan , Shenbo Xu , Mingyu Jin , William Yang Wang , Rameswar Panda , Yikang Shen

Generative AI has recently propelled the decoding of images from brain activity. How do these approaches scale with the amount and type of neural recordings? Here, we systematically compare image decoding from four types of non-invasive…

Image and Video Processing · Electrical Eng. & Systems 2025-01-29 Hubert Banville , Yohann Benchetrit , Stéphane d'Ascoli , Jérémy Rapin , Jean-Rémi King

Scaling laws describe how model performance grows with data, parameters and compute. While large datasets can usually be collected at relatively low cost in domains such as language or vision, scientific machine learning is often limited by…

Machine Learning · Computer Science 2025-11-04 Paul Setinek , Gianluca Galletti , Johannes Brandstetter

Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models across many different…

Machine Learning · Computer Science 2024-10-03 Yangjun Ruan , Chris J. Maddison , Tatsunori Hashimoto

Large foundation models are typically trained on data from multiple domains, with the data mixture--the proportion of each domain used--playing a critical role in model performance. The standard approach to selecting this mixture relies on…

Machine Learning · Computer Science 2025-10-03 Mustafa Shukor , Louis Bethune , Dan Busbridge , David Grangier , Enrico Fini , Alaaeldin El-Nouby , Pierre Ablin

Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for…

Machine Learning · Computer Science 2024-01-05 Shashank Subramanian , Peter Harrington , Kurt Keutzer , Wahid Bhimji , Dmitriy Morozov , Michael Mahoney , Amir Gholami

Low-precision training is critical for optimizing the trade-off between model quality and training costs, necessitating the joint allocation of model size, dataset size, and numerical precision. While empirical scaling laws suggest that…

Machine Learning · Statistics 2026-02-27 Dechen Zhang , Xuan Tang , Yingyu Liang , Difan Zou

Neural scaling laws predict how language model performance improves with increased training inputs. While aggregate metrics like validation loss can follow smooth power-law curves, individual downstream tasks exhibit diverse scaling…

Machine Learning · Computer Science 2026-05-11 Michael Y. Hu , Jane Pan , Ayush Rajesh Jhaveri , Nicholas Lourie , Kyunghyun Cho