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.
xVal tokenizes numbers continuously for better scientific model training.
Galactica learns from scientific literature to help researchers.
EduQG generates better educational questions by pre-training on scientific text.
The paper argues for prioritizing identifying structure over complex models for scientific discovery.
Paper outlines a new mathematical language for experiments.
iPrompt uses LLMs to generate natural-language explanations of data patterns.
CausalEvolve improves efficiency and discovery in open-ended scientific tasks.
Numeracy is the ability to understand and work with numbers. It is a necessary skill for composing and understanding documents in clinical, scientific, and other technical domains. In this paper, we explore different strategies for modelling numerals with language models, such as memorisation and digit-by-digit composi…
ParaMonte simplifies Monte Carlo simulations for various scientific fields.
Genomic models learn DNA sequences to predict functions.
New framework reveals thermodynamic principles for LLM training.
New method extracts biological concepts from cell microscopy images.
ChemCrow enhances LLMs for chemistry tasks, automating complex chemical processes.
Natural language processing often involves computations with semantic or syntactic graphs to facilitate sophisticated reasoning based on structural relationships. While convolution kernels provide a powerful tool for comparing graph structure based on node (word) level relationships, they are difficult to customize and…
Biomedical research papers use significantly different language and jargon when compared to typical English text, which reduces the utility of pre-trained NLP models in this domain. Meanwhile Medline, a database of biomedical abstracts, introduces nearly a million new documents per-year. Applications that could benefit…
Fine-tunes language models with captions for differential equation solving.
The scientific literature is a rich source of information for data mining with conceptual knowledge graphs; the open science movement has enriched this literature with complementary source code that implements scientific models. To exploit this new resource, we construct a knowledge graph using unsupervised learning me…
Model learns code representations from comments for data analysis tasks.
Enhances drug discovery models by understanding human language.
Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models. However, applications to science remain limited because of the impracticability of rewriting complex scientific simulators in a PPL, the computational cost of inference, and the …
Many research fields codify their findings in standard formats, often by reporting correlations between quantities of interest. But the space of all testable correlates is far larger than scientific resources can currently address, so the ability to accurately predict correlations would be useful to plan research and a…
Framework evaluates AI proposals for drug discovery, finds no LLM advantage.
The semantic map calibrates uncertainty from language model probabilities.
LLMs fail to match statistical ground truth despite stable run-to-run performance.
ParaDRAM automates parallel MCMC simulations across languages.
This paper surveys UQ methods for deep learning.
Study uses machine learning to predict predator-prey dynamics without prior knowledge.
There has been a lot of recent interest in adopting machine learning methods for scientific and engineering applications. This has in large part been inspired by recent successes and advances in the domains of Natural Language Processing (NLP) and Image Classification (IC). However, scientific and engineering problems …
Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated method for connecting scientific literature to synthesis insights. Starting from natural la…
The study uncovers latent capabilities of language models via causal representation learning.
Scientific Computing relies on executing computer algorithms coded in some programming languages. Given a particular available hardware, algorithms speed is a crucial factor. There are many scientific computing environments used to code such algorithms. Matlab is one of the most tremendously successful and widespread s…
CausalGame benchmarks LLM agents' causal thinking in games.
New method uses LLMs to generate detailed scientific hypotheses.
This paper introduces Sigma, a domain-specific computational representation for collaboration in large-scale for the field of economics. A computational representation is not a programming language or a software platform. A computational representation is a domain-specific representation system based on three specific …
Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their innate ambiguity, a Word Sense Disambiguation (WSD) algorithm can avoid numbers…
Remasking improves the quality of discrete diffusion models for natural language and image generation.
Celeste is a procedure for inferring astronomical catalogs that attains state-of-the-art scientific results. To date, Celeste has been scaled to at most hundreds of megabytes of astronomical images: Bayesian posterior inference is notoriously demanding computationally. In this paper, we report on a scalable, parallel v…
Data mining revealed a cluster of economic, psychological, social and cultural indicators that in combination predicted corruption and wealth of European nations. This prosperity syndrome of self-reliant citizens, efficient division of labor, a sophisticated scientific community, and respect for the law, was clearly di…
Planetary exploration missions with Mars rovers are complicated, which generally require elaborated task planning by human experts, from the path to take to the images to capture. NASA has been using this process to acquire over 22 million images from the planet Mars. In order to improve the degree of automation and th…
Study bandwidth-limited training and inference of language models.
The study examines how much data is needed for generative and vision-language models to make reliable predictions.
Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.
Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of da…
Paper proposes a new framework for hypothesis testing in imaging.
Accelerometer measurements are the prime type of sensor information most think of when seeking to measure physical activity. On the market, there are many fitness measuring devices which aim to track calories burned and steps counted through the use of accelerometers. These measurements, though good enough for the aver…
New benchmarks show LLMs struggle with causal discovery.
Symbolic regression is a powerful technique that can discover analytical equations that describe data, which can lead to explainable models and generalizability outside of the training data set. In contrast, neural networks have achieved amazing levels of accuracy on image recognition and natural language processing ta…
We describe a new method for visualizing topics, the distributions over terms that are automatically extracted from large text corpora using latent variable models. Our method finds significant -grams related to a topic, which are then used to help understand and interpret the underlying distribution. Compared with …