works on

From the 1 of 9 linked papers with an AI index.

collaborators

9 papers

cs.LG2026

AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs

Yiming Zhang, Koji Tsuda

Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, and links. TogoMCP helps langu…

cs.AI2026

SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation

Yiming Zhang, Koji Tsuda

The paper introduces SAGA, a training‑free framework that uses schema constraints to guide the grounding of natural‑language questions into SPARQL queries, improving the accuracy o…

cond-mat.mtrl-sci2026

NIMO: A Software Platform for Closed-Loop Materials Exploration with Diverse AI Algorithms

Ryo Tamura, Naruki Yoshikawa, Koji Tsuda +1

Self-driving laboratories (SDLs), where artificial intelligence proposes subsequent experiments and robotic systems execute them, are rapidly becoming the vanguard of materials dis…

cs.AI2026

ProvMind: Provenance-grounded reasoning for materials synthesis

Yiming Zhang, Ryo Tamura, Koji Tsuda

Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten synthesis procedures into text…

cond-mat.mtrl-sci2026

LLM-guided phase diagram construction through high-throughput experimentation

Ryo Tamura, Haruhiko Morito, Yuna Oikawa +7

Constructing phase diagrams for multicomponent alloys requires extensive experimental measurements and is a time-consuming task. Here we investigate whether large language models (…

physics.comp-ph2026

Update of PHYSBO: Improving Usability and Portability of Bayesian Optimization for Physics and Materials Research

Yuichi Motoyama, Kazuyoshi Yoshimi, Tatsumi Aoyama +3

Bayesian optimization (BO) is widely used to accelerate physics and materials research, where objective function evaluations are computationally or experimentally expensive. While…