Browse State-of-the-Art › Physical Intuition

Physical Intuition

15 papers with code · 1 benchmark · 1 dataset archive 2025-07-28

MethodologyMiscellaneousReasoning

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 35 · with a code link: 15 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 35 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 35 of 35, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 8 Dec 2021 3 repositories listed
    Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world.
  • 3 Mar 2016 3 repositories listed
    Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world.
  • We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget.
  • 9 May 2025 1 repository listed
    Next, we present the Corrective Force Prediction Network (CFP-Net), which uses complementary representations for point-level analysis to simulate the different contributions from internal and external corrective forces.
  • 1 Feb 2025 1 repository listed
    While existing deep learning based methods conduct RME given spectrum measurements gathered from dispersed sensors in the region of interest, they rely on centralized data at a fusion center, which however raises…
  • 12 Sep 2024 1 repository listed
    Here, we develop InvDesFlow, an AI search engine that integrates deep model pre-training and fine-tuning techniques, diffusion models, and physics-based approaches (e. g., first-principles electronic structure…
  • 14 Nov 2023 1 repository listed
    Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus…
  • 8 Oct 2023 1 repository listed
    Here we demonstrate and experimentally validate an ML approach that incorporates physical intuition to infer force laws in a laboratory dusty plasma.
  • 8 Aug 2023 1 repository listed
    Specifically, we learn three interpretable thermodynamic coordinates and build a dynamical landscape of polymer stretching, including the identification of stable and transition states and the control of the stretching…
  • 26 May 2023 1 repository listed
    One of the primary reasons behind the success of neural networks has been the emergence of an array of new, highly-successful optimizers, perhaps most importantly the Adam optimizer.
  • 21 Jun 2020 1 repository listed
    In this work, we frame the multi-layer optical design task as a sequence generation problem.
  • 8 Apr 2020 1 repository listed
    Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set.
  • 22 Dec 2019 1 repository listed
    While variational autoencoders ensure continuity of the embedding by assuming a unimodal Gaussian prior, this is at odds with the multi-basin free-energy landscapes that typically arise from the identification of…
  • 12 Jun 2018 1 repository listed
    Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has become increasingly popular for simulating posterior samples in large-scale Bayesian modeling.
  • 21 Apr 2018 1 repository listed
    Physical intuition is pivotal for intelligent agents to perform complex tasks.
  • Can Theoretical Physics Research Benefit from Language Agents?
    6 Jun 2025 0 repositories listed
    Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics research is not yet mature.
  • Large Language Models and Mathematical Reasoning Failures
    17 Feb 2025 0 repositories listed
    This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems.
  • Towards understanding how attention mechanism works in deep learning
    24 Dec 2024 0 repositories listed
    Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks.
  • A Note on Spectral Map
    5 Dec 2024 0 repositories listed
    In molecular dynamics (MD) simulations, transitions between states are often rare events due to energy barriers that exceed the thermal temperature.
  • Automated design of nonreciprocal thermal emitters via Bayesian optimization
    13 Sep 2024 0 repositories listed
    Nonreciprocal thermal emitters that break Kirchhoff's law of thermal radiation promise exciting applications for thermal and energy applications.
  • Optimizing Cycle Life Prediction of Lithium-ion Batteries via a Physics-Informed Model
    26 Apr 2024 0 repositories listed
    Accurately measuring the cycle lifetime of commercial lithium-ion batteries is crucial for performance and technology development.
  • Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning
    30 May 2022 0 repositories listed
    Recent progress in machine learning methods, and the emerging availability of programmable interfaces for scanning probe microscopes (SPMs), have propelled automated and autonomous microscopies to the forefront of…
  • Wind Park Power Prediction: Attention-Based Graph Networks and Deep Learning to Capture Wake Losses
    10 Jan 2022 0 repositories listed
    With the increased penetration of wind energy into the power grid, it has become increasingly important to be able to predict the expected power production for larger wind farms.
  • Analytical Modelling of Exoplanet Transit Specroscopy with Dimensional Analysis and Symbolic Regression
    22 Dec 2021 0 repositories listed
    The physical characteristics and atmospheric chemical composition of newly discovered exoplanets are often inferred from their transit spectra which are obtained from complex numerical models of radiative transfer.
  • Convolutional Neural Networks Demystified: A Matched Filtering Perspective Based Tutorial
    26 Aug 2021 0 repositories listed
    Deep Neural Networks (DNN) and especially Convolutional Neural Networks (CNN) are a de-facto standard for the analysis of large volumes of signals and images.
  • Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
    3 May 2021 0 repositories listed
    People often use physical intuition when manipulating articulated objects, irrespective of object semantics.
  • Why is AI hard and Physics simple?
    31 Mar 2021 0 repositories listed
    We discuss why AI is hard and why physics is simple.
  • Advances in Bayesian Probabilistic Modeling for Industrial Applications
    26 Mar 2020 0 repositories listed
    Industrial applications frequently pose a notorious challenge for state-of-the-art methods in the contexts of optimization, designing experiments and modeling unknown physical response.
  • Portfolio Cuts: A Graph-Theoretic Framework to Diversification
    12 Oct 2019 0 repositories listed
    Investment returns naturally reside on irregular domains, however, standard multivariate portfolio optimization methods are agnostic to data structure.
  • Guiding Physical Intuition with Neural Stethoscopes
    1 May 2019 0 repositories listed
    Model interpretability and systematic, targeted model adaptation present central challenges in deep learning.
  • Biophysics at the coffee shop: lessons learned working with George Oster
    20 Feb 2019 0 repositories listed
  • What is the Machine Learning?
    28 Sep 2017 0 repositories listed
  • Combining Machine Learning and Physics to Understand Glassy Systems
    23 Sep 2017 0 repositories listed
  • Generalizable Features From Unsupervised Learning
    12 Dec 2016 0 repositories listed
  • A Complete Recipe for Stochastic Gradient MCMC
    15 Jun 2015 0 repositories listed

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections