Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

3567131,0691,425 · Jun 202019922001200920172026
48 results for scientific foundation models

A new method calibrates scientific models by adding randomness to their predictions.

problem Current scientific foundation models lack calibrated uncertainty.
method Stochastic Attention, which randomizes attention weights using multinomial samples.
result Stochastic Attention achieves the strongest native calibration and sharpest prediction intervals.

New method extracts biological concepts from cell microscopy images.

problem Extracting meaningful concepts from vision foundation models trained on cell microscopy images.
method Sparse dictionary learning (DL) combined with PCA whitening pre-processing.
result Successfully retrieved biologically meaningful concepts like cell types and genetic perturbations.

xVal tokenizes numbers continuously for better scientific model training.

problem Lack of continuous numerical tokenization for scientific datasets in LLMs.
method xVal: Continuous numerical tokenization strategy.
result xVal outperforms other numerical tokenization methods on scientific datasets.

Differentiable programming aids in solving differential equations and their sensitivities.

problem Computing gradients of numerical solutions of differential equations.
method Review of existing techniques and mathematical foundations.
result Established a coherent framework for combining differential equations with data-driven approaches.

Foundation models fail to preserve continuous geometry, identified as the Geometric Alignment Tax.

problem Continuous geometry is lost in foundation models due to discrete categorical bottlenecks.
method Controlled ablations on synthetic systems and evaluation of 14 biological models using rate-distortion theory and MINE.
result Replacing cross-entropy with a continuous head reduces geometric distortion by up to 8.5x.

CDFM aims to unify causal discovery across diverse datasets.

problem Fragmented, test-driven causal discovery approaches struggle with modern data heterogeneity.
method CDFM is a unified, general-purpose framework using a variational decomposition of causal mechanisms.
result CDFM outperforms traditional algorithms across diverse datasets.

Foundation models alter medical data science workflow, challenging veridical data science principles.

problem Foundation models disrupt traditional data science practices in medicine.
method Critically examined the medical foundation model lifecycle and its deviation from veridical data science principles.
result Foundation models challenge veridical data science principles of predictability, computability, and stability.

This work bridges stochastic interpolants to infinite-dimensional Hilbert spaces.

problem Limited flexibility in generating arbitrary distributions for function-valued data.
method Establishes a rigorous framework for stochastic interpolants in infinite-dimensional Hilbert spaces.
result Achieves state-of-the-art results in conditional generation for complex PDE-based benchmarks.

TDL uses topological features for deep learning models, promising new insights and solutions.

problem Lack of comprehensive theoretical foundations and practical benefits in TDL.
method Discussing open problems and potential solutions in TDL.
result TDL can complement existing graph and geometric learning methods.

Geometric framework detects concept frustration between human concepts and machine representations.

problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.

New method uses LLMs to generate detailed scientific hypotheses.

problem Generating detailed, actionable scientific hypotheses from coarse initial directions.
method Hierarchical search method that incrementally adds details to hypotheses.
result Hierarchical search method consistently outperforms strong baselines on expert-annotated hypotheses.

Review of diffusion models for SBI in non-ideal data scenarios.

problem Inference of parameters from complex simulation outputs with intractable likelihoods.
method Diffusion models for likelihood-free inference, addressing model misspecification, unstructured observations, and missing data.
result Improved robustness and efficiency in SBI methods for non-ideal data scenarios.

Efficiently tests two distributions using Nyström approximation of MMD.

problem Testing whether two sets of data are from the same distribution in large-scale scenarios.
method Nyström approximation of maximum mean discrepancy (MMD) for scalable testing.
result Finite-sample bound on power of the test for sufficiently separated distributions.

CViT learns complex physical systems using vision transformer techniques.

problem Learning maps between infinite-dimensional function spaces in scientific machine learning.
method Combines vision transformer encoder, grid-based coordinate embedding, and cross-attention mechanism.
result Achieves state-of-the-art performance on multiple benchmarks, often surpassing larger models.

We provide scientific foundations for athletic performance prediction on an individual level, exposing the phenomenology of individual athletic running performance in the form of a low-rank model dominated by an individual power law. We present, evaluate, and compare a selection of methods for prediction of individual …

2015-05-05abs ↗pdf ↗

Peer review is the foundation of scientific publication, and the task of reviewing has long been seen as a cornerstone of professional service. However, the massive growth in the field of machine learning has put this community benefit under stress, threatening both the sustainability of an effective review process and…

2018-12-18abs ↗pdf ↗

Galactica learns from scientific literature to help researchers.

problem Information overload in scientific literature makes it hard to find useful insights.
method Trained on a large corpus of scientific papers, reference material, and knowledge bases.
result Outperforms existing models on various scientific tasks, including LaTeX equations and mathematical reasoning.

Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.

problem Estimating unknown parameters in hybrid models combining machine learning and scientific models.
method Sharpness-aware minimization adapted for hybrid modeling, focusing on model simplicity.
result Demonstrates effectiveness of SAM-based hybrid model learning for scientific parameter estimation.

TabMGP uses a martingale posterior with TabPFN to estimate uncertainty in tabular data.

problem Estimating uncertainty in models like TabPFN for scientific estimands θθ.
method TabMGP is an MGP built on TabPFN, focusing inference on loss function-defined parameters.
result TabMGP produces credible sets with near-nominal coverage and often outperforms baselines.

In this paper we form a general conservation law that unifies a class of physics field theories. For this we first introduce the notion of a general field as a formal sum differential forms on a Minkowski manifold. Thereafter, we employ the action principle to define the conservation law for such general fields. By con…

2019-08-28abs ↗pdf ↗

Bayesian deep learning improves deep learning's capabilities across diverse settings.

problem Overlooked metrics, tasks, and data types in deep learning.
method Revisits strengths of Bayesian deep learning and addresses challenges.
result Bayesian deep learning can elevate deep learning's capabilities across diverse settings.

New framework assesses extreme errors in machine learning models.

problem Current validation methods fail to quantify extreme errors in high-stakes domains.
method Uses Extreme Value Theory (EVT) to estimate worst-case failures.
result Establishes EVT as a fundamental tool for assessing model reliability.

MDNs offer a data-efficient alternative to diffusion and flow models for multimodal scientific learning.

problem Capturing multimodal conditional uncertainty in scientific inverse problems.
method Mixture Density Networks (MDNs) as explicit parametric density estimators.
result MDNs achieve superior generalization, interpretability, and sample efficiency in scientific tasks.

SOS-VAE improves generative models for scientific applications by correcting decoder bias.

problem Bias in generative parameters due to supervised learning in VAEs.
method Develops SOS-VAE framework to influence decoder for predictive latent representation.
result Ensures reliable generative parameters for scientific applications.

EduQG generates better educational questions by pre-training on scientific text.

problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.

New AI approach improves quantum device calibration by leveraging prior scientific discoveries.

problem Lack of abundant data in scientific disciplines hinders model generalizability.
method Introduces a new machine learning approach that combines prior scientific knowledge with data.
result Accuracy in predicting quantum device energy spectrum surpasses current state-of-the-art by over 20%.

Revises Bayesian model averaging for foundation models.

problem Ensemble pre-trained and lightly-finetuned foundation models for improved classification performance.
method Introduces trainable linear classifiers and computationally cheaper model averaging scheme (OMA).
result Ensembled models can better predict on various datasets.

Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured poi…

2019-09-07abs ↗pdf ↗

Social media enhances or diminishes scientific status, depending on usage.

problem Impact of social media on scientific stratification and mobility.
method Logistic Attribution Analysis combining statistical and machine learning methods.
result Social media promotes stratification and mobility, but beyond a threshold, it negatively impacts status.

Time series foundation models are well-calibrated, improving over baseline models.

problem Calibration of time series foundation models for practical applications.
method Systematic evaluations of five time series foundation models and two baselines, assessing calibration, prediction heads, and long-term forecasting.
result Time series foundation models are consistently better calibrated than baseline models and do not show over- or under-confidence.

CARVE validates clustering results using resampling and stability analysis.

problem Inconsistent and unreliable clustering results due to algorithm, preprocessing, and kk sensitivity.
method CARVE uses resampling-based validation and stability analysis to evaluate multiple clustering algorithms and hyperparameters.
result CARVE consistently recovers near-optimal clusterings and finer biological structure.

Introduces foundation priors for using model-generated data in empirical research.

problem Using model-generated data as real observations in empirical research.
method Introduces foundation priors as an exponential-tilted, generalized Bayesian update of the user's primitive prior.
result Synthetic data reflects both model patterns and user's priors, enabling principled use in empirical work.