10 papers
Coverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis
Xuemin Chen, Xiaozhuang Song, Xinjian Zhao +2
Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among several precursor sets for t…
RetroGEF: Dynamic Graph Edit Flow for Single-Step Retrosynthesis
Xiaozhuang Song, Xuemin Chen, Xinjian Zhao +2
Retrosynthesis enables the discovery of viable synthetic routes to target molecules. It plays a central role in modern drug discovery and materials design. Retrosynthesis involves…
When Vision Meets Graphs: A Survey on Graph Reasoning and Learning
Xinjian Zhao, Wei Pang, Zhixuan Yu +8
Graphs are a fundamental data structure underlying many problems in the natural and social sciences. Over the past decade, Graph Neural Networks (GNNs) have dominated graph machine…
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models
Xinjian Zhao, Xiangru Jian, Yaoyao Xu +4
Molecular embedding models can serve as foundational infrastructure for computational chemistry and drug discovery, where reusable vector representations support property predictio…
Closed-Loop Molecular Inverse Design with Semantic LLM Surrogates
Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song +2
Practical molecular inverse design is rarely a one-shot generation problem; it often involves enriching a pool of molecules that match a desired property profile under a limited or…
The Underappreciated Power of Vision Models for Graph Structural Understanding
Xinjian Zhao, Wei Pang, Zhongkai Xue +6
Graph Neural Networks operate through bottom-up message-passing, fundamentally differing from human visual perception, which intuitively captures global structures first. We invest…
TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles
Yaoyao Xu, Di Wang, Zihan Zhou +2
Understanding the dynamic behavior of proteins is critical to elucidating their functional mechanisms, yet generating realistic, temporally coherent trajectories of protein ensembl…
Enhancing Graph Self-Supervised Learning with Graph Interplay
Xinjian Zhao, Wei Pang, Xiangru Jian +3
Graph self-supervised learning (GSSL) has emerged as a compelling framework for extracting informative representations from graph-structured data without extensive reliance on labe…
Boosting Protein Language Models with Negative Sample Mining
Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song +2
We introduce a pioneering methodology for boosting large language models in the domain of protein representation learning. Our primary contribution lies in the refinement process f…
Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning
Xiangru Jian, Xinjian Zhao, Wei Pang +4
The recent surge in contrast-based graph self-supervised learning has prominently featured an intensified exploration of spectral cues. Spectral augmentation, which involves modify…