4 citations · 8 across the 15 of their papers we have counts for
16 papers
Divergence Decoding: Training-Free Capability Fusion
Yimi Wang, Hao Li, Shuo Yang +6
While large language models excel in reasoning, these generalists often lack knowledge for specialized scientific domains. Conversely, domain models~(specialists), while knowledgea…
Harnessing agent memory to build lifelong AI partners for materials scientists
Siyu Liu, Bo Hu, Beilin Ye +3
Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or experiments, and judgement t…
Augmenting Molecular Language Models with Local -gram Memory
Xinni Zhang, Zijing Liu, He Cao +2
Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to rep…
Improving Cross-Format Robustness in Language Models with Multi-Format Training
June M. Liu, Shaomian Zheng, He Cao +3
Large language models often remain sensitive to answer format: a question solved correctly in one form may fail in another semantically equivalent form. To study this gap, we defin…
From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models
Hongyu Guo, Hao Li, He Cao +2
Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical failure mode: a model may o…
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
Xinwu Ye, He Cao, Hao Li +5
Biomolecular generators are often adapted with reward feedback to improve task-specific utility, but pushing utility alone can concentrate generation on a narrow family of candidat…
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
Qingchuan Zhang, He Cao, Hao Li +6
Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-model approaches typically t…
ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
Yulin Zhang, He Cao, Zihao Jiang +6
Designing proteins with desired functions or properties represents a core goal in synthetic biology and drug discovery. Recent advances in protein language models (PLMs) have enabl…
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
Yunhong Lu, Qichao Wang, Hengyuan Cao +2
Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose…
ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams
Qiang Xu, Shengyuan Bai, Yu Wang +6
Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological str…
Mozi: Governed Autonomy for Drug Discovery LLM Agents
He Cao, Siyu Liu, Fan Zhang +7
Tool-augmented large language model (LLM) agents promise to unify scientific reasoning with computation, yet their deployment in high-stakes domains like drug discovery is bottlene…
Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis
Hao Li, He Cao, Shenyao Peng +7
Language models are revolutionizing the biochemistry domain, assisting scientists in drug design and chemical synthesis with high efficiency. Yet current approaches struggle betwee…
From Static Structures to Ensembles: Studying and Harnessing Protein Structure Tokenization
Zijing Liu, Bin Feng, He Cao +1
Protein structure tokenization converts 3D structures into discrete or vectorized representations, enabling the integration of structural and sequence data. Despite many recent wor…
Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations
Hao Li, He Cao, Bin Feng +6
While large language models (LLMs) with Chain-of-Thought (CoT) reasoning excel in mathematics and coding, their potential for systematic reasoning in chemistry, a domain demanding…
Rethinking Text-based Protein Understanding: Retrieval or LLM?
Juntong Wu, Zijing Liu, He Cao +6
In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding. Current approaches focus on integrating protein-…
How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension
Hao Li, Liuzhenghao Lv, He Cao +6
Large language models are increasingly used in scientific domains, especially for molecular understanding and analysis. However, existing models are affected by hallucination issue…