Mingyu Derek Ma

Machine Learning Scientist@Genentech·美国·OpenReview

研究方向

AI4Science · generative language modeling · language modeling · large language models · natural language processing · information extraction · event understanding · machine learning · deep learning

4.5

MatSciBench: Benchmarking the Reasoning Ability of LLM in Materials Science

ICLR 2026Desk Rejected

6.6

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation

ICML 2025Poster

二作

6.0

CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making

ICLR 2025Rejected

一作

3.0

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection

合作者 (20)

Mingyu Derek Ma

MatSciBench: Benchmarking the Reasoning Ability of LLM in Materials Science

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation

GIVE: Structured Reasoning with Knowledge Graph Inspired Veracity Extrapolation

MIRAI: Evaluating LLM Agents for International Event Forecasting

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection