ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “physics”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CVRecentJun 2, 2026

NewtPhys: Do Foundation Models Understand Newtonian Physics?

Sebastian Cavada, Soumava Paul, Tuan-Hung Vu, Andrei Bursuc +1 more

The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dense physical annotations, to systematically evaluate and reveal the limitations of foundation models in low-level Newtonia…

View →
cs.LGcs.AIRecentMay 28, 2026

Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts

Mengdi Chu, Yang Liu, Ayan Biswas, Han-Wei Shen

The paper introduces a comprehensive benchmark to test if physics foundation models learn generalizable dynamics, finding that their performance is highly conditional and not universally general.

View →
cs.AIEmpiricalRecentNov 4, 2026

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

Bingran You, Wenjun Ke, Ria Rosenauer, Bo Liu +68 more

The paper introduces FrontierPhysics, an end-to-end benchmark for evaluating AI agents in physics research.

View →
stat.MLcs.LGhep-phEmpiricalRecentJun 18, 2026

Statistical Properties of Training & Generalization

Itay Lavie, Noam Levi, Yonatan Kahn

This paper investigates deep learning from a physics-informed perspective, examining its key features and surprises.

View →
cs.LGcs.AIRecentMay 31, 2026

Physics-Informed Deep Learning for Entropy Prediction in Heterogeneous Systems: Thermodynamic and Information-Theoretic Case Studies

Biswajeet Sahoo, Debadutta Patra

The paper introduces a unified Physics-Informed Deep Learning (PIDL) framework that simultaneously enforces physical laws and information-theoretic bounds, demonstrating robust, domain-agnostic entrop…

View →
cs.AIcond-mat.mtrl-sciphysics.comp-phEmpiricalComprehensiveRecentJul 2, 2026

Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics

Haonan Huang

An autonomous research agent is developed to automate end-to-end LLM in high-stakes scientific domains, specifically condensed matter physics, by mapping the corpus, calibrating methodology, conductin…

View →
cs.CLcs.AIcs.MAEmpiricalRecentOct 27, 2026

Can LLMs Uncover Hidden Physical Laws through Free Exploration?

Zhen Yang, Wen Wang, Xander Xu, Ying-Cong Chen

This paper evaluates the ability of large language models to discover physical laws through experimentation.

View →
cs.CVcs.RORecentJun 2, 2026

SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image

Inhee Lee, Sangwon Baik, Sungjoo Kim, Hyeonwoo Kim +2 more

SimuScene introduces a novel compositional 3D reconstruction pipeline that integrates physics simulation directly into the shape and layout estimation process to generate stable, simulation-ready 3D s…

View →
cs.ETcs.ARcs.CVEmpiricalRecentOct 24, 2026

Optimizing Physical Neural Networks through Device Variable Selection

Sjoerd van den Belt, Manuel Escudero, Mohamadreza Zolfagharinejad, Wilfred G. van der Wiel +1 more

This paper improves the efficiency and accuracy of physical neural networks by leveraging device physics and trainable routing between signals.

View →
cs.AIcs.CVRecentMay 28, 2026

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

Nafiul Haque, Syed Nazmus Sakib, Shifat E Arman

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by explicitly enforcing physical laws and geometric constraints, significantly outperforming c…

View →
cs.DMcs.NEnlin.PSTheoreticalRecentJul 21, 2026

Towards chemistries in dynamical systems

Martin Biehl, Nathaniel Virgo

This paper proposes a method to describe dynamical systems using molecular and reaction concepts, making three key decisions: number of places, species determination, and transitions.

View →
cs.AIastro-ph.COcs.HCRecentMay 28, 2026

Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software

Nhat-Minh Nguyen

This case study demonstrates that in complex scientific software development, human domain expertise and careful supervision are more critical to ensuring the trustworthiness of AI-generated code than…

View →
cs.AIcs.CLTheoreticalRecentAug 14, 2026

LLMs Don't Pay for the Jump

Paras Balani, Subhrakanta Panda

This paper argues that Large Language Models lack the ability to perform abductive reasoning like Einstein due to the absence of physical cost for epistemic error, and proposes a thermodynamic couplin…

View →
cs.AIcond-mat.stat-mechcs.ITEmpiricalRecentJun 18, 2026

Thermodynamic Measure of Intelligence

Ishanu Chattopadhyay

Intelligence can be measured through recursive self-simulation

View →
cs.NEcs.AIRecentMay 27, 2026

Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization

Helena Stegherr, Michael Heider, Nils Meyer, Tobias Thummerer +6 more

This paper analyzes the performance and explainability requirements of evolutionary algorithms when applied to complex, real-world physics-informed optimization problems, identifying a gap between cur…

View →
physics.flu-dyncs.AIcs.LGRecentMay 31, 2026

Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence

Payel Mukhopadhyay, Stefan S. Nixon, Romain Watteaux, Michael McCabe +19 more

The authors demonstrate that a physics foundation model, finetuned on simulation data, can successfully predict complex laboratory fluid dynamics, specifically resolving a long-standing discrepancy in…

View →
cs.NEcs.AIEmpiricalRecentJul 17, 2026

Evolutionary Algorithm-Guided LLMs for Physics-Informed Neural Network Design

Xu Yang, Mingyang Yu, Jing Xu, Keqian Li

A closed-loop evolutionary algorithm is proposed to guide a large language model in generating complete and executable physics-informed neural network configurations, using measured training outcomes…

View →
eess.IVcs.AIRecentMay 29, 2026

A physics-informed foundation model for quantitative diffusion MRI

Zihan Li, Jialan Zheng, Ziyu Li, Xun Yuan +17 more

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

View →