From the 1 of 6 linked papers with an AI index.
6 papers
Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science
Sutanay Choudhury, Jeffrey J. Czajka, Lummy M. O. Monteiro +15
The paper presents Mycelium, an active shared workspace that links human researchers and AI agents by capturing observations and hypotheses, maintaining a evolving knowledge model,…
Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypotheses
Sutanay Choudhury, Anwesha Banerjee, Udishnu Sanyal +7
Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error experimentation and computatio…
Optimizing Data Distribution and Kernel Performance for Efficient Training of Chemistry Foundation Models: A Case Study with MACE
Jesun Firoz, Franco Pellegrini, Mario Geiger +17
Chemistry Foundation Models (CFMs) that leverage Graph Neural Networks (GNNs) operating on 3D molecular graph structures are becoming indispensable tools for computational chemists…
Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events
Stefan Dernbach, Alejandro Michel, Khushbu Agarwal +3
This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a fra…
ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback
Henry W. Sprueill, Carl Edwards, Khushbu Agarwal +6
The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided co…
GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding
Stefan Dernbach, Khushbu Agarwal, Alejandro Zuniga +2
Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As…