most citedThe Liver Tumor Segmentation Benchmark (LiTS)

1.2k citations · 1.2k across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular Design

Yongjun Jeong, Hanbum Ko, Ye Rin Kim +6

Real-world molecular design remains challenging for large language model (LLM)-based agents. It requires them to interpret design contexts, satisfy multiple constraints, identify i…