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.
We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials. Although this was a new task, we had a total of 26 submissions across 3 evaluation scenarios. We expect the tas…
GSR optimizes tasks in scientific workflows, improving performance across diverse applications.
Galactica learns from scientific literature to help researchers.
Keyphrase boundary classification (KBC) is the task of detecting keyphrases in scientific articles and labelling them with respect to predefined types. Although important in practice, this task is so far underexplored, partly due to the lack of labelled data. To overcome this, we explore several auxiliary tasks, includ…
New AI approach improves quantum device calibration by leveraging prior scientific discoveries.
A dataset for evaluating engagement with scientific video lectures.
CausalEvolve improves efficiency and discovery in open-ended scientific tasks.
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge. In particular, one may infer from them relations between scientific concepts, such as synonyms and hyponyms. Artificial neural networks have been recently explored for relation extraction. In this work, we continue…
New framework compresses and recovers scientific data efficiently.
MDNs offer a data-efficient alternative to diffusion and flow models for multimodal scientific learning.
Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthet…
LLMs fail to match statistical ground truth despite stable run-to-run performance.
Survey of deep learning models for scientific discovery.
A new method calibrates scientific models by adding randomness to their predictions.
Model learns code representations from comments for data analysis tasks.
A multi-task model tackles citation purpose classification with limited data.
Machine learning algorithms such as linear regression, SVM and neural network have played an increasingly important role in the process of scientific discovery. However, none of them is both interpretable and accurate on nonlinear datasets. Here we present contextual regression, a method that joins these two desirable …
This paper introduces a new task to better understand Transformers in quantitative contexts.
The process of collecting and organizing sets of observations represents a common theme throughout the history of science. However, despite the ubiquity of scientists measuring, recording, and analyzing the dynamics of different processes, an extensive organization of scientific time-series data and analysis methods ha…
Automatic classification of scientific articles based on common characteristics is an interesting problem with many applications in digital library and information retrieval systems. Properly organized articles can be useful for automatic generation of taxonomies in scientific writings, textual summarization, efficient…
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…
A new method combines SciML and UQ with physical constraints.
Enhances KANs for accuracy and interpretability with multi-exit architecture.
The key to success in machine learning (ML) is the use of effective data representations. Traditionally, data representations were hand-crafted. Recently it has been demonstrated that, given sufficient data, deep neural networks can learn effective implicit representations from simple input representations. However, fo…
Deep Learning has managed to push boundaries in a wide variety of tasks. One area of interest is to tackle problems in reasoning and understanding, with an aim to emulate human intelligence. In this work, we describe a deep learning model that addresses the reasoning task of question-answering on categorical plots. We …
Synthetic data can be used to ask more questions and accelerate discovery with provable validity guarantees.
Finding a well-performing architecture is often tedious for both DL practitioners and researchers, leading to tremendous interest in the automation of this task by means of neural architecture search (NAS). Although the community has made major strides in developing better NAS methods, the quality of scientific empiric…
SGNNs use simulations to train neural networks, improving scientific forecasting and interpretability.
Sparse random features improve accuracy in data-scarce settings.
The paper clarifies conditions for using benchmark scores in machine learning.
ChemCrow enhances LLMs for chemistry tasks, automating complex chemical processes.
PDBAL targets experiments for probabilistic models to maximize insights.
New method speeds up model selection for complex scientific tasks.
New method uses LLMs to generate detailed scientific hypotheses.
Study uses machine learning to predict predator-prey dynamics without prior knowledge.
Novel framework for ML-assisted inference valid for any statistical task.
xVal tokenizes numbers continuously for better scientific model training.
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…
Sparse mapping has been a key methodology in many high-dimensional scientific problems. When multiple tasks share the set of relevant features, learning them jointly in a group drastically improves the quality of relevant feature selection. However, in practice this technique is used limitedly since such grouping infor…
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…
Social media enhances or diminishes scientific status, depending on usage.
Posterior inference with an intractable likelihood is becoming an increasingly common task in scientific domains which rely on sophisticated computer simulations. Typically, these forward models do not admit tractable densities forcing practitioners to make use of approximations. This work introduces a novel approach t…
Evidence shows that in a significant number of cases the current methods of research do not allow for reproducible and falsifiable procedures of scientific investigation. As a consequence, the majority of critical decisions at all levels, from personal investment choices to overreaching global policies, rely on some va…
There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-driven fashion. However, a common challenge is to verify the scientific plausibility or validity of outputs predicted by a neural network. This w…
Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.
Paper introduces MTGP for engineering tasks with sparse data.
AutoSciDACT detects scientific anomalies in noisy data.
SBI uses neural networks to infer model parameters from simulators.