AI4Science

Mathematics

• Solving olympiad geometry without human demonstrations
• LLEMMA: AN OPEN LANGUAGE MODEL FOR MATHEMATICS
• Lego-prover: Neural theorem proving with growing libraries
• Baldur: Whole-Proof Generation and Repair with Large Language Models
• Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
• Formal mathematics statement curriculum learning
• DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function
• LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
• Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving
• Thor: Wielding hammers to integrate language models and automated theorem provers
• Hypertree proof search for neural theorem proving
• Proof artifact co-training for theorem proving with language models
• LISA: Language models of ISAbelle proofs
• Generative language modeling for automated theorem proving
• First Experiments with Neural Translation of Informal to Formal Mathematics

Biochemistry

• Universal chemical programming language for robotic synthesis repeatability
• DrugAssist: A Large Language Model for Molecule Optimization
• Large language models direct automated chemistry laboratory
• Chatgpt research group for optimizing the crystallinity of mofs and cofs
• BioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
• ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
• ChemCrow: Augmenting large-language models with chemistry tools
• Retrieved Sequence Augmentation for Protein Representation Learning
• Natural language processing models that automate programming will transform chemistry research and teaching
• Organic synthesis in a modular robotic system driven by a chemical programming language