Scientific Machine Learning

ICML 2024arXiv:2405.09783

#2

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery

Pingchuan Ma, Johnson Tsun-Hsuan Wang, Minghao Guo et al.

bilevel optimizationconstitutive law discoverymolecular designscientific generative agent+4

67

ICLR 2025arXiv:2404.18400

#3

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

Parshin Shojaee, Kazem Meidani, Shashank Gupta et al.

symbolic regressionscientific equation discoverylarge language modelsevolutionary search+3

57

ICLR 2025arXiv:2407.01725

#4

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal et al.

data-driven discoverylarge language modelscode generationfunction calling+4

40

ICML 2024arXiv:2402.17879

#5

Automated Statistical Model Discovery with Language Models

Michael Li, Emily Fox, Noah Goodman

statistical model discoveryprobabilistic programminglanguage model automationbox's loop framework+3

30

ICML 2025arXiv:2504.10415

#6

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

Parshin Shojaee, Ngoc Hieu Nguyen, Kazem Meidani et al.

28

COLM 2025arXiv:2504.05108

#7

Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning

Anja Šurina, Amin Mansouri, Lars C.P.M. Quaedvlieg et al.

Large Language ModelsReinforcement LearningEvolutionary SearchAlgorithm Discovery+2

25

ICML 2024arXiv:2402.07318

#8

Position: Optimization in SciML Should Employ the Function Space Geometry

Johannes Müller, Marius Zeinhofer

function space geometryinfinite-dimensional optimizationscientific machine learningoptimize then discretize+1

19

NEURIPS 2025arXiv:2506.10521

#9

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Yuhao Zhou, Yiheng Wang, Xuming He et al.

multimodal large language modelsscientific signal perceptionscientific attribute understandingscientific comparative reasoning+4

18

NEURIPS 2025arXiv:2507.02554

#10

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Edan Toledo, Karen Hambardzumyan, Martin Josifoski et al.

ai research agentsautomated machine learningsearch policiesmcts algorithms+4

16

ICML 2024arXiv:2402.13077

#11

Mechanistic Neural Networks for Scientific Machine Learning

Adeel Pervez, Francesco Locatello, Efstratios Gavves

governing differential equationsmechanistic neural networksrelaxed linear programmingscientific machine learning+4

12

battery degradation modelingmachine learning platformenergy storagedata preprocessing+3

#12

BatteryML: An Open-source Platform for Machine Learning on Battery Degradation

Han Zhang, Xiaofan Gui, Shun Zheng et al.

ICLR 2024

11

CVPR 2024arXiv:2403.01053

#13

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling

Jianan Fan, Dongnan Liu, Hang Chang et al.

10

NEURIPS 2025arXiv:2506.15692

#14

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Jaehyun Nam, Jinsung Yoon, Jiefeng Chen et al.

code generation agentsmachine learning engineeringfeature engineeringablation study guidance+4

9

NEURIPS 2025arXiv:2503.13497

#15

Is Limited Participant Diversity Impeding EEG-based Machine Learning?

Philipp Bomatter, Henry Gouk

4

CVPR 2025arXiv:2502.10060

#16

DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery

Utkarsh Mall, Cheng Perng Phoo, Mia Chiquier et al.

3

NEURIPS 2025arXiv:2507.00310

#17

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

Dhruv Agarwal, Bodhisattwa Prasad Majumder, Reece Adamson et al.

autonomous scientific discoverybayesian surprisemonte carlo tree searchhypothesis generation+4

3

NEURIPS 2025arXiv:2510.23166

#18

Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms

Philippe Wyder, Judah Goldfeder, Alexey Yermakov et al.

3

NEURIPS 2025arXiv:2506.07619

#19

The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning

Toby Boyne, Juan Campos, Rebecca Langdon et al.

yield predictionsolvent selectiontransfer learningactive learning+4

2

ICML 2025arXiv:2503.06366

#20

Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics

Herman Chau, Helen Jenne, Davis Brown et al.

2

NEURIPS 2025arXiv:2510.21935

#21

AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing

Sam Bright-Thonney, Christina Reissel, Gaia Grosso et al.

novelty detectioncontrastive learninganomaly detectiondimensionality reduction+3

2

AAAI 2025arXiv:2412.12347

#22

Can Private Machine Learning Be Fair?

Joseph Rance, Filip Svoboda

AutoSciLab: A Self-Driving Laboratory for Interpretable Scientific Discovery

Saaketh Desai, Sadhvikas Addamane, Jeffrey Y. Tsao et al.

self-driving laboratoryvariational autoencoderactive learningdirectional autoencoder+4

NEURIPS 2025arXiv:2510.25368

#24

Position: Biology is the Challenge Physics-Informed ML Needs to Evolve

Julien Martinelli

NEURIPS 2025arXiv:2506.08516

#25

ML4CFD Competition: Results and Retrospective Analysis

Mouadh Yagoubi, David Danan, Milad LEYLI ABADI et al.

ICML 2025arXiv:2412.16247

#26

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models

Konstantin Donhauser, Kristina Ulicna, Gemma Moran et al.

#27

Position: Is machine learning good or bad for the natural sciences?

David W. Hogg, Soledad Villar

causal inferenceconfounder representationmachine learning ontologymachine learning epistemology+4

#28

Position: Mission Critical – Satellite Data is a Distinct Modality in Machine Learning

Esther Rolf, Konstantin Klemmer, Caleb Robinson et al.

satellite data modalitymultispectral imagery analysisgeospatial machine learningtemporal data modeling+4

ICML 2025arXiv:2408.05215

#29

PhysPDE: Rethinking PDE Discovery and a Physical HYpothesis Selection Benchmark

Mingquan Feng, Yixin Huang, Yizhou Liu et al.

Physics-Informed Weakly Supervised Learning For Interatomic Potentials

Makoto Takamoto, Viktor Zaverkin, Mathias Niepert

#31

Position: $C^*$-Algebraic Machine Learning $-$ Moving in a New Direction

Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri

c*-algebraic machine learningkernel methodsneural networksunified learning frameworks+1

AAAI 2024arXiv:2512.11133

#32

Machine Learning

Powered Combinatorial Clock Auction - Ermis Nikiforos Soumalias, Jakob Weissteiner, Jakob Heiss et al.

particle physicspattern recognitionpredictive modelingalgorithmic learning+2

ICML 2024arXiv:2405.02952

#33

Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving

Sohei Arisaka, Qianxiao Li

gradient estimation techniquemeta-learning techniqueshyperparameter selectionlegacy numerical solvers+3

#34

Data Debugging with Shapley Importance over Machine Learning Pipelines

Bojan Karlaš, David Dao, Matteo Interlandi et al.

Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation

Bohan Lyu, Yadi Cao, Duncan Watson-Parris et al.

Position: Data-driven Discovery with Large Generative Models

Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal et al.

large generative modelsdata-driven discoveryautomated hypothesis verificationend-to-end systems+3

#37

Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy

Lucas Spangher, Allen Wang, Andrew Maris et al.

disruption predictionsimulation modelingpartially observed datafusion controls+3