English
Related papers

Related papers: Spend Less, Fit Better: Budget-Efficient Scaling L…

200 papers

Scaling test-time compute is a promising axis for improving LLM capabilities. However, test-time compute can be scaled in a variety of ways, and effectively combining different approaches remains an active area of research. Here, we explore…

Machine Learning · Computer Science 2025-02-04 Ryan Ehrlich , Bradley Brown , Jordan Juravsky , Ronald Clark , Christopher Ré , Azalia Mirhoseini

Active Learning (AL) is a powerful tool for learning with less labeled data, in particular, for specialized domains, like legal documents, where unlabeled data is abundant, but the annotation requires domain expertise and is thus expensive.…

Computation and Language · Computer Science 2022-11-16 Sepideh Mamooler , Rémi Lebret , Stéphane Massonnet , Karl Aberer

The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources. Most current approaches either rely…

Machine Learning · Computer Science 2024-10-16 Yiding Jiang , Allan Zhou , Zhili Feng , Sadhika Malladi , J. Zico Kolter

Given a fixed budget for total model size, one must choose between training a single large model or combining the predictions of multiple smaller models. We investigate this trade-off for ensembles of random-feature ridge regression models…

Machine Learning · Computer Science 2025-10-28 Benjamin S. Ruben , William L. Tong , Hamza Tahir Chaudhry , Cengiz Pehlevan

We study the problem of experiment planning with function approximation in contextual bandit problems. In settings where there is a significant overhead to deploying adaptive algorithms -- for example, when the execution of the data…

Machine Learning · Computer Science 2024-01-11 Aldo Pacchiano , Jonathan N. Lee , Emma Brunskill

A framework is introduced for actively and adaptively solving a sequence of machine learning problems, which are changing in bounded manner from one time step to the next. An algorithm is developed that actively queries the labels of the…

Machine Learning · Computer Science 2018-05-31 Yuheng Bu , Jiaxun Lu , Venugopal V. Veeravalli

A data mixture refers to how different data sources are combined to train large language models, and selecting an effective mixture is crucial for optimal downstream performance. Existing methods either conduct costly searches directly on…

Machine Learning · Computer Science 2026-05-07 Jingwei Li , Xinran Gu , Jingzhao Zhang

A common workflow for many engineering design problems requires the evaluation of the design system to be investigated under a range of conditions. These conditions usually involve a combination of several parameters. To perform a complete…

Computational Engineering, Finance, and Science · Computer Science 2020-09-18 J. H. Gaspar Elsas , N. A. G. Casaprima , I. F. M. Menezes

Test-time scaling (TTS) has been shown to improve the performance of large language models (LLMs) by sampling and aggregating diverse reasoning paths. However, existing research has overlooked a critical issue: selection bias of reasoning…

Artificial Intelligence · Computer Science 2025-09-24 Zongqian Wu , Baoduo Xu , Tianyu Li , Zhu Sun , Xiaofeng Zhu , Lei Feng

Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning -- spending tokens when they improve reliability and stopping early when…

Artificial Intelligence · Computer Science 2026-05-15 Xi Wang , Anushri Suresh , Alvin Zhang , Rishi More , William Jurayj , Benjamin Van Durme , Mehrdad Farajtabar , Daniel Khashabi , Eric Nalisnick

Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as repeated sampling, self-correction, and tree search,…

Artificial Intelligence · Computer Science 2026-04-30 Zhimin Lin , Yixin Ji , Jinpeng Li , Yu Luo , Dong Li , Junhua Fang , Juntao Li , Min Zhang

When solving decision and optimisation problems, many competing algorithms (model and solver choices) have complementary strengths. Typically, there is no single algorithm that works well for all instances of a problem. Automated algorithm…

Machine Learning · Computer Science 2025-06-11 Erdem Kuş , Özgür Akgün , Nguyen Dang , Ian Miguel

The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation remains largely unexplored. In this paper, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Shunlin Lu , Jingbo Wang , Zeyu Lu , Ling-Hao Chen , Wenxun Dai , Junting Dong , Zhiyang Dou , Bo Dai , Ruimao Zhang

Domain reweighting is an emerging research area aimed at adjusting the relative weights of different data sources to improve the effectiveness and efficiency of LLM pre-training. We show that data mixtures that perform well at smaller…

Machine Learning · Computer Science 2025-10-03 Feiyang Kang , Yifan Sun , Bingbing Wen , Si Chen , Dawn Song , Rafid Mahmood , Ruoxi Jia

Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and…

Machine Learning · Computer Science 2026-04-13 Matthew DosSantos DiSorbo , Harang Ju

Test-time scaling has emerged as a powerful technique for enhancing the reasoning capabilities of large language models. However, its effectiveness in medical reasoning remains uncertain, as the medical domain fundamentally differs from…

Computation and Language · Computer Science 2026-02-19 Xiaoke Huang , Juncheng Wu , Hui Liu , Xianfeng Tang , Yuyin Zhou

High-fidelity physics simulations are powerful tools in the design and optimization of charged particle accelerators. However, the computational burden of these simulations often limits their use in practice for design optimization and…

Accelerator Physics · Physics 2020-04-15 Auralee Edelen , Nicole Neveu , Yannick Huber , Mattias Frey , Christopher Mayes , Andreas Adelmann

Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter selection. While scaling laws provide valuable guidance on model size and data requirements,…

Machine Learning · Computer Science 2026-05-21 Xingyu Xie , Kuangyu Ding , Shuicheng Yan , Kim-Chuan Toh , Tianwen Wei

We introduce MODEL SELECTOR, a framework for label-efficient selection of pretrained classifiers. Given a pool of unlabeled target data, MODEL SELECTOR samples a small subset of highly informative examples for labeling, in order to…

Machine Learning · Computer Science 2024-10-28 Patrik Okanovic , Andreas Kirsch , Jannes Kasper , Torsten Hoefler , Andreas Krause , Nezihe Merve Gürel

Recent work has demonstrated that pre-training in-domain language models can boost performance when adapting to a new domain. However, the costs associated with pre-training raise an important question: given a fixed budget, what steps…

Computation and Language · Computer Science 2022-05-16 Fan Bai , Alan Ritter , Wei Xu