Related papers: Procedural Knowledge Libraries: Towards Executable…

Automatically tuning parallel compute kernels allows libraries and frameworks to achieve performance on a wide range of hardware, however these techniques are typically focused on finding optimal kernel parameters for particular input sizes…

This paper presents Deepchecks, a Python library for comprehensively validating machine learning models and data. Our goal is to provide an easy-to-use library comprising of many checks related to various types of issues, such as model…

Knowledge tracing (KT), aiming to mine students' mastery of knowledge by their exercise records and predict their performance on future test questions, is a critical task in educational assessment. While researchers achieved tremendous…

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore…

Recent explorations of large-scale pre-trained language models (PLMs) have revealed the power of PLMs with huge amounts of parameters, setting off a wave of training ever-larger PLMs. However, it requires tremendous computational resources…

Large language models (LLMs) exhibit remarkable capabilities in question answering and reasoning thanks to their extensive parametric memory. However, their knowledge is inherently limited by the scope of their pre-training data, while…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental question: How can we verify that an LLM's reasoning is…

Computational notebooks are notoriously prone to reproducibility failures. By permitting out-of-order cell execution, notebooks accumulate hidden state and implicit dependencies that cause interactive executions to silently diverge from…

We introduce ReservoirComputing.jl, an open source Julia library for reservoir computing models. The software offers a great number of algorithms presented in the literature, and allows to expand on them with both internal and external…

Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective strategy, and the…

Several recent efforts have been devoted to enhancing pre-trained language models (PLMs) by utilizing extra heterogeneous knowledge in knowledge graphs (KGs) and achieved consistent improvements on various knowledge-driven NLP tasks.…

This paper represents an approach to creating global knowledge systems, using new philosophy and infrastructure of global distributed semantic network (frame knowledge representation system) based on the space-time database construction.…

Large Language Models (LLMs) offer a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred. Consequently, a key research challenge is to transcend traditional knowledge…

Personal Knowledge Graphs (PKGs) are introduced by the semantic web community as small-sized user-centric knowledge graphs (KGs). PKGs fill the gap of personalised representation of user data and interests on the top of big,…

Jupyter notebooks have become central in data science, integrating code, text and output in a flexible environment. With the rise of machine learning (ML), notebooks are increasingly used for prototyping and data analysis. However, due to…

The trend toward open science increases the pressure on authors to provide access to the source code and data they used to compute the results reported in their scientific papers. Since sharing materials reproducibly is challenging, several…

Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of…

Machine learning solutions are very popular in the field of chemoinformatics, where they have numerous applications, such as novel drug discovery or molecular property prediction. Molecular fingerprints are algorithms commonly used for…

Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously…