English
Related papers

Related papers: Assessing the Extrapolation Capability of Template…

200 papers

Canonical work handling distribution shifts typically necessitates an entire target distribution that lands inside the training distribution. However, practical scenarios often involve only a handful of target samples, potentially lying…

Machine Learning · Computer Science 2025-01-17 Lingjing Kong , Guangyi Chen , Petar Stojanov , Haoxuan Li , Eric P. Xing , Kun Zhang

Modern foundation models exhibit remarkable out-of-distribution (OOD) generalization, solving tasks far beyond the support of their training data. However, the theoretical principles underpinning this phenomenon remain elusive. This paper…

Machine Learning · Statistics 2025-05-29 Jiawei Ge , Amanda Wang , Shange Tang , Chi Jin

Nonlinear response theory, in contrast to linear cases, involves (dynamical) details, and this makes application to many body systems challenging. From the microscopic starting point we obtain an exact response theory for a small number of…

Statistical Mechanics · Physics 2018-05-09 Urna Basu , Laurent Helden , Matthias Krüger

Machine learning systems perform well on pattern matching tasks, but their ability to perform algorithmic or logical reasoning is not well understood. One important reasoning capability is algorithmic extrapolation, in which models trained…

Machine Learning · Computer Science 2022-10-18 Arpit Bansal , Avi Schwarzschild , Eitan Borgnia , Zeyad Emam , Furong Huang , Micah Goldblum , Tom Goldstein

Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure. While such models allow one to generate molecules with desirable properties, they give no guarantees…

Machine Learning · Computer Science 2019-12-05 John Bradshaw , Brooks Paige , Matt J. Kusner , Marwin H. S. Segler , José Miguel Hernández-Lobato

It is a long-standing question in origin-of-life research whether the information content of replicating molecules can be maintained in the presence of replication errors. Extending standard quasispecies models of non-enzymatic replication,…

Populations and Evolution · Quantitative Biology 2009-12-03 B. Obermayer , E. Frey

We develop a new approximation theory for linear and quadratic interpolation models, suitable for use in convex-constrained derivative-free optimization (DFO). Most existing model-based DFO methods for constrained problems assume the…

Optimization and Control · Mathematics 2024-03-25 Lindon Roberts

Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles--a phenomenon we characterize as the "plausibility-validity gap." This challenge proves especially acute in…

Machine Learning · Computer Science 2026-01-07 Malikussaid , Hilal Hudan Nuha , Isman Kurniawan

The field of computer-aided synthesis planning (CASP) has seen rapid advancements in recent years, achieving significant progress across various algorithmic benchmarks. However, chemists often encounter numerous infeasible reactions when…

Machine Learning · Computer Science 2024-09-09 Shang Xiang , Lin Yao , Zhen Wang , Qifan Yu , Wentan Liu , Wentao Guo , Guolin Ke

Given the importance of nuclear mass predictions, numerous models have been developed to extrapolate the measured data into unknown regions. While neural networks -- the core of modern artificial intelligence -- have been recently suggested…

Nuclear Theory · Physics 2025-07-11 C. H. Kim , K. Y. Chae , M. S. Smith

Polymer models are a widely used tool to study the prebiotic formation of metabolism at the origins of life. Counts of the number of reactions in these models are often crucial in probabilistic arguments concerning the emergence of…

Molecular Networks · Quantitative Biology 2021-04-14 Oliver Weller-Davies , Mike Steel , Jotun Hein

Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language models (VLMs)…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Yuanwei Hu , Bo Peng , Yadan Luo , Zhen Fang , Ling Chen , Jie Lu

Recent advancements in machine learning have showcased its potential to significantly accelerate the discovery of new materials. Central to this progress is the development of rapidly computable property predictors, enabling the…

Materials Science · Physics 2024-04-16 Kohei Noda , Araki Wakiuchi , Yoshihiro Hayashi , Ryo Yoshida

A recently developed model chemistry (jun-Cheap) has been slightly modified and proposed as an effective, reliable and parameter-free scheme for the computation of accurate reaction rates with special reference to astrochemical and…

Chemical Physics · Physics 2021-06-25 Vincenzo Barone , Jacopo Lupi , Zoi Salta , Nicola Tasinato

Chemical reactions are the fundamental building blocks of drug design and organic chemistry research. In recent years, there has been a growing need for a large-scale deep-learning framework that can efficiently capture the basic rules of…

Machine Learning · Computer Science 2024-03-08 Bo Qiang , Yiran Zhou , Yuheng Ding , Ningfeng Liu , Song Song , Liangren Zhang , Bo Huang , Zhenming Liu

Retrosynthesis planning, essential in organic synthesis and drug discovery, has greatly benefited from recent AI-driven advancements. Nevertheless, existing methods frequently face limitations in both applicability and explainability.…

Computational Engineering, Finance, and Science · Computer Science 2025-07-24 Situo Zhang , Hanqi Li , Lu Chen , Zihan Zhao , Xuanze Lin , Zichen Zhu , Bo Chen , Xin Chen , Kai Yu

Accurate de novo molecular and materials design requires structure-property models that generalize beyond known regimes. Although pretrained atomistic models achieve strong in-distribution accuracy after fine-tuning, their reliability under…

Computational Physics · Physics 2026-01-14 Chengqian Zhang , Duo Zhang , Anyang Peng , Mingyu Guo , Yuzhi Zhang , Lei Wang , Guolin Ke , Linfeng Zhang , Tiejun Li , Han Wang

Retrosynthesis is the task of planning a series of chemical reactions to create a desired molecule from simpler, buyable molecules. While previous works have proposed algorithms to find optimal solutions for a range of metrics (e.g.…

Artificial Intelligence · Computer Science 2024-04-16 Austin Tripp , Krzysztof Maziarz , Sarah Lewis , Marwin Segler , José Miguel Hernández-Lobato

Transformer-based large language models have remarkable potential to accelerate design optimization for applications such as drug development and materials discovery. Self-supervised pretraining of transformer models requires large-scale…

Machine Learning · Computer Science 2023-10-27 Pei Zhang , Logan Kearney , Debsindhu Bhowmik , Zachary Fox , Amit K. Naskar , John Gounley

Molecular foundation models are rapidly advancing scientific discovery, but their unreliability on out-of-distribution (OOD) samples severely limits their application in high-stakes domains such as drug discovery and protein design. A…

Machine Learning · Computer Science 2025-10-01 Langzhou He , Junyou Zhu , Fangxin Wang , Junhua Liu , Haoyan Xu , Yue Zhao , Philip S. Yu , Qitian Wu
‹ Prev 1 3 4 5 6 7 10 Next ›