Weijian Lin — accepted AI-conference papers

2025

Reinforcement Learning for Charged Particle Beam Control to Minimize Injection Mismatch in Particle Accelerators

Thilina Balasooriya, Shinjae Yoo, Vincent Schoefer, Huan-Hsin Tseng, Yuan Gao, Weijian Lin +1

ICASSP 2025accepted

Particle accelerators are composed of various components, and their properties are finely tuned to optimize certain particle beam qualities as they accelerate. In particular, particle colliders like the Relativistic Heavy Ion Collider (RHIC) at Brookhaven National Lab (BNL) are interested in maximiz…

Cited by 0 Source ↗Scholar ↗

2025

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen +8

ACL 2025long

Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models (LLMs). However, progress has been hindered by a lack of reliable evaluation datasets. To address this, we present ToolHop, a dataset comprisi…

Cited by 0 Source ↗PDF ↗Scholar ↗