PULSE: Our community science stream

  • ENDORSEMENTDec. 8, 2023, 9:49 a.m.
    Large Language Models for Mathematicians

    Large language models (LLMs) such as ChatGPT have received immense interest for their general-purpose language understanding and, in particular, their ability to generate high-quality text …

  • CODEDec. 6, 2023, 11 p.m.
    GOLEM

    GOLEM is a method for causal discovery. It formulates a likelihood-based score function with soft sparsity and DAG constraints for learning linear DAGs, which guarantees …

  • CLUBDec. 5, 2023, 10:43 a.m.
    ML reading group

    ML reading group

    Kayewords: Machine learning
  • ENDORSEMENTDec. 4, 2023, 2:33 a.m.
    Language Models: A Guide for the Perplexed

    Given the growing importance of AI literacy, we decided to write this tutorial to help narrow the gap between the discourse among those who study …

  • ENDORSEMENTDec. 1, 2023, 9:27 a.m.
    Large Language Models as Tool Makers

    Recent research shows the potential of enhancing the problem-solving ability of large language models (LLMs) through the use of external tools. However, prior work along …

  • CODENov. 30, 2023, 10:21 a.m.
    GNoME

    From microchips to batteries and photovoltaics, discovery of inorganic crystals is a fundamental problem in materials science. Graph Networks for Materials Science (GNoME) is a …

  • CODENov. 30, 2023, 3:52 a.m.
    Jeometric

    A Python library for Graph Neural Networks (GNNs) in JAX.

  • CODENov. 29, 2023, 9:37 a.m.
    GTP-ViT

    The official GTP-ViT code for token summarisation for efficient vision transformers via graph-based token propagation.

  • ENDORSEMENTNov. 28, 2023, 8:45 p.m.
    Poisoning Web-Scale Training Datasets is Practical

    Deep learning models are often trained on distributed, webscale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that …

  • ENDORSEMENTNov. 27, 2023, 10:17 a.m.
    Scaling Laws for Neural Language Models

    We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and …

  • CLUBNov. 27, 2023, 4:41 a.m.
    Paidy ML paper reading

    To practice reading and learning from ML-related papers Date and time prepared each month

    Kayewords: Machine Learning
  • ENDORSEMENTNov. 25, 2023, 9:36 a.m.
    Context-Aware Graph Attention Networks

    Graph Neural Networks (GNNs) have been widely studied for graph data representation and learning. However, existing GNNs generally conduct context-aware learning on node feature representation …