Xiaohui Chen

Joined

May 2021

Names

Xiaohui Chen (Preferred)

Emails

****@tufts.edu (Confirmed)

,

****@tufts.edu (Confirmed)

Personal Links

Semantic Scholar

Career & Education History

PhD student

Tufts University (tufts.edu)

2021 – 2025

Advisors, Relations & Conflicts

PhD Advisor

2020 – 2025

Expertise

Graph generation

2021 – Present

representation learniing

2021 – Present

Publications

GRAPH GENERATIVE PRE-TRAINED TRANSFORMER
Xiaohui Chen, Yinkai Wang, Jiaxing He, Yuanqi Du, Soha Hassoun, Xiaolin Xu, Liping Liu
- ICLR 2025 DeLTa Workshop Poster
- Readers: Everyone
Large Language Model is Secretly a Protein Sequence Optimizer
Yinkai Wang, Jiaxing He, Yuanqi Du, Xiaohui Chen, Jianan Canal Li, Liping Liu, Xiaolin Xu, Soha Hassoun
- ICLR 2025 Workshop LMRL
- Readers: Everyone
Graph Generative Pre-trained Transformer
Xiaohui Chen, Yinkai Wang, Jiaxing He, Yuanqi Du, Soha Hassoun, Xiaolin Xu, Liping Liu
- ICML 2025 poster
- Readers: Everyone
MADGEN: Mass-Spec attends to De Novo Molecular generation
Yinkai Wang, Xiaohui Chen, Liping Liu, Soha Hassoun
- ICLR 2025 Poster
- Readers: Everyone
EDGE++: Improved Training and Sampling of EDGE
Xiaohui Chen, Mingyang Wu, Liping Liu
- SyntheticData4ML 2023 Poster
- Readers: Everyone
EDGE++: Improved Training and Sampling of EDGE
Xiaohui Chen, Mingyang Wu, Liping Liu
- NeurIPS 2023 GLFrontiers Workshop Poster
- Readers: Everyone
WL-Tree: a New Tool for Analyzing Graph Neural Networks
Liping Liu, Jiaxing He, Jacob Boerma, Xiaohui Chen
- Submitted to ICLR 2024
- Readers: Everyone
On Separate Normalization in Self-supervised Transformers
Xiaohui Chen, Yinkai Wang, Yuanqi Du, Soha Hassoun, Liping Liu
- NeurIPS 2023 poster
- Readers: Everyone
Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
Xiaohui Chen, Jiaxing He, Xu Han, Liping Liu
- ICML 2023 Poster
- Readers: Everyone
Fitting Autoregressive Graph Generative Models through Maximum Likelihood Estimation
Xu Han, Xiaohui Chen, Francisco J. R. Ruiz, Li-Ping Liu
- J. Mach. Learn. Res. 2023
- Readers: Everyone

View all 18 publications

Co-Authors