collaborators

7 papers

cs.DB2026

Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation

Mingwei Ye, Jiaxi Zhuang, Mingjun Xu +3

Natural Language to MongoDB Query Language (NL2MQL) is essential for democratizing access to modern document-centric databases. Unlike Text-to-SQL, NL2MQL faces unique challenges f…

cs.CV2026

APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation

Dongliang Chen, Xinlin Zhuang, Junjie Xu +8

Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to…

cs.LG2025

Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis

Jiaxi Zhuang, Yu Zhang, Aimin Zhou +1

Retrosynthesis prediction is fundamental to drug discovery and chemical synthesis, requiring the identification of reactants that can produce a target molecule. Current template-fr…

cs.LG2025

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Jiaxi Zhuang, Yaorui Shi, Jue Hou +8

Molecular property prediction is crucial for drug discovery and materials science, yet existing approaches suffer from limited interpretability, poor cross-task generalization, and…

cs.LG2025

ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information

Jiaxi Zhuang, Yu Zhang, Yan Zhang +2

Motivation: Retrosynthesis plays a crucial role in organic synthesis and drug discovery, focusing on identifying a set of reactants capable of synthesizing a target product molecul…

cs.CL2025

Doc2SAR: A Synergistic Framework for High-Fidelity Extraction of Structure-Activity Relationships from Scientific Documents

Jiaxi Zhuang, Kangning Li, Jue Hou +3

Extracting molecular structure-activity relationships (SARs) from scientific literature and patents is essential for drug discovery and materials research. However, this task remai…