Difference between revisions of "Science Agents"

From GISAXS
Jump to: navigation, search
Line 1: Line 1:
  
 +
=AI Use-cases for Science=
 +
 +
==Literature==
 +
===AI finding links in literature==
 +
* 2024-11: [https://doi.org/10.1038/s41562-024-02046-9  Large language models surpass human experts in predicting neuroscience results]
  
=AI Use-cases for Science=
 
 
==Autonomous Ideation==
 
==Autonomous Ideation==
 
* 2024-09: [https://arxiv.org/abs/2409.14202 Mining Causality: AI-Assisted Search for Instrumental Variables]
 
* 2024-09: [https://arxiv.org/abs/2409.14202 Mining Causality: AI-Assisted Search for Instrumental Variables]

Revision as of 15:24, 13 December 2024

AI Use-cases for Science

Literature

=AI finding links in literature

Autonomous Ideation

Adapting LLMs to Science

AI/ML Methods tailored to Science

Symbolic Regression

Literature Discovery

Commercial

AI/ML Methods co-opted for Science

Mechanistic Interpretability

Train large model on science data. Then apply mechanistic interpretability (e.g. sparse autoencoders, SAE) to the feature/activation space.

Uncertainty


Science Agents

AI Science Systems

Inorganic Materials Discovery

Chemistry

Impact of AI in Science

Related Tools

Data Visualization

See Also