Liuzhenghao Lv 吕刘正浩

I am a Ph.D. student in the School of Computer Science at Peking University, advised by Prof. Yonghong Tian (co-advised by Prof. Li Yuan).

My research lies at the intersection of scientific foundation models, molecular and protein LLMs, scientific agents, and scientific evaluation, with a focus on models and agentic systems that understand, generate, and reason over molecules, proteins, and biological protocols.

Google Scholar GitHub Hugging Face

Research Interests

Scientific Foundation Models

Large-scale models for scientific representation learning, generation, and reasoning.

Molecular and Protein LLMs

Language-model-driven molecular design, protein understanding, and protein sequence generation.

Scientific Agents

Tool-augmented agents, workflow automation, and biological protocol reasoning.

Scientific Evaluation

Hallucination evaluation, benchmark construction, and reliability analysis for scientific LLMs.

Education

Ph.D. Student, Computer Science, Peking University (Successive Postgraduate and Doctoral Programs)

School of Computer Science · 2025.09 - 2028.06 (expected)

M.Phil. Student, Computer Science, Peking University

School of Electronic and Computer Engineering · 2023.09 - 2025.06

B.Eng., Information Security, Tongji University

School of Electronic and Information Engineering · 2019.09 - 2023.07

Selected Publications

2026 Nat.
Commun.

Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding

Liuzhenghao Lv^*, Hao Li^*, Yu Wang, Zijun Chen, Zhiyuan Yan, Zongying Lin, Yuyang Liu, Li Yuan, Yonghong Tian

Nature Communications

^* Equal contribution.

Paper Code Dataset

2026 ICML

Bridging the Gap in Autonomous Science: The Corpus and Benchmark for Biological Protocol Reasoning

Yuyang Liu^*, Liuzhenghao Lv^*, Xiancheng Zhang, Jingya Wang, Li Yuan, Yonghong Tian

International Conference on Machine Learning (ICML 2026)

^* Equal contribution

Paper Code Dataset

2026 ACL Oral

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

Yuyang Liu, Jingya Wang, Liuzhenghao Lv, Yonghong Tian

Annual Meeting of the Association for Computational Linguistics (ACL 2026)

Oral Presentation

Paper Code Project

2025 IEEE TAI

ProLLaMA: A Protein Large Language Model for Multitask Protein Language Processing

Liuzhenghao Lv, Zongying Lin, Hao Li, Yuyang Liu, Jiaxi Cui, Calvin Yu-Chian Chen, Li Yuan, Yonghong Tian

IEEE Transactions on Artificial Intelligence

Paper Code

2025 NeurIPS
AI4Sci.

How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension

Hao Li^*, Liuzhenghao Lv^*, He Cao, Zijing Liu, Zhiyuan Yan, Yu Wang, Yonghong Tian, Yu Li, Li Yuan

NeurIPS 2025 Workshop on AI for Science

^* Equal contribution

Paper OpenReview

2024 SCIS

TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation

Zongying Lin, Hao Li, Liuzhenghao Lv, Yu Wang, Bin Lin, Junwu Zhang, Zijun Chen, Calvin Yu-Chian Chen, Li Yuan, Yonghong Tian

Science China Information Sciences

Paper arXiv

2024 ICASSP

Optimal ANN-SNN Conversion with Group Neurons

Liuzhenghao Lv, Wei Fang, Li Yuan, Yonghong Tian

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)

Paper Code

2023 GPB

HPC-Atlas: Computationally Constructing a Comprehensive Atlas of Human Protein Complexes

Yuliang Pan, Ruiyi Li, Wengen Li, Liuzhenghao Lv, Jihong Guan, Shuigeng Zhou

Genomics, Proteomics & Bioinformatics

Paper Code

2023 arXiv

Machine Mindset: An MBTI Exploration of Large Language Models

Jiaxi Cui^*, Liuzhenghao Lv^*, Jing Wen, Rongsheng Wang, Jing Tang, Yonghong Tian, Li Yuan

arXiv

^* Equal contribution

Paper Code

Experience

Ph.D. and M.Phil. Researcher, Peking University

Beijing / Shenzhen, China · 2023.09 - Present. Research on HME, ProLLaMA, BioProBench, BioProAgent, and reliability evaluation for scientific LLMs.

First Student Contributor, AI for Science Platform, Peking University

Beijing / Shenzhen, China · 2025 - Present. Contributing to digital laboratory workflows and experimental-protocol agents for scientific automation.

Research Intern, Peking University HSBC Business School

Shenzhen, China · 2023.10 - 2024.05. Applied retrieval-augmented generation to AI-related patent identification and patent corpus analysis.

Official Contributor, SpikingJelly

Open-source deep learning framework for spiking neural networks · 2023. Contributed to a widely used SNN framework recommended by Nature Computational Science.

Backend R&D Intern, ByteDance

Shanghai, China · 2022.08 - 2022.11. Backend research and development for production software systems.