activity
20242026
collaborators

15 papers

cs.LG2026

VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention

Jingbo Zhou, Jun Xia, Siyuan Li +11

Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models…

cs.LG2026

Instructor-inspired Machine Learning for Robust Molecular Property Prediction

Fang Wu, Shuting Jin, Siyuan Li +1

Machine learning catalyzes a revolution in chemical and biological science. However, its efficacy heavily depends on the availability of labeled data, and annotating biochemical da…

cs.LG2026

Discovering the Representation Bottleneck of Graph Neural Networks

Fang Wu, Siyuan Li, Stan Z. Li

Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different…

cs.LG2025

Multimodal Regression for Enzyme Turnover Rates Prediction

Bozhen Hu, Cheng Tan, Siyuan Li +4

The enzyme turnover rate is a fundamental parameter in enzyme kinetics, reflecting the catalytic efficiency of enzymes. However, enzyme turnover rates remain scarce across most org…

cs.CL2025

ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference

Qi Chen, Jingxuan Wei, Zhuoya Yao +5

Understanding how scientific ideas evolve requires more than summarizing individual papers-it demands structured, cross-document reasoning over thematically related research. In th…

cs.AI2025

SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches

Cheng Tan, Qi Chen, Jingxuan Wei +6

Hand-drawn sketches are a natural and efficient medium for capturing and conveying ideas. Despite significant advancements in controllable natural image generation, translating fre…