weitao Du
9 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird 🏆 Grand Slam
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Machine Learning
(7)
Deep Learning
(6)
Architectures
(4)
Core Methods
(4)
Models
(3)
Optimization & Theory
(3)
Artificial Intelligence
(2)
Interdisciplinary
(2)
Core AI
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Science
(2)
Mathematics & Optimization
(1)
Bayesian & Probabilistic
(1)
Mathematics
(1)
Keywords
geometric deep learning
(3)
graph neural network
(3)
diffusion model
(3)
neural network optimization
(2)
molecule representation
(2)
stochastic differential equation
(2)
drug discovery
(2)
geometric representation
(2)
mutual information
(1)
molecular graph
(1)
variational inference
(1)
equivariant neural network
(1)
training dynamics
(1)
denoising diffusion
(1)
generative model
(1)
molecular representation
(1)
crystalline material
(1)
molecular geometry
(1)
equivariant graph neural network
(1)
riemannian geometry
(1)
Papers
GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation
AAAI 2025
A Flexible Diffusion Model
ICML 2023
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
ICML 2023
A new perspective on building efficient and expressive 3D equivariant graph neural networks
NeurIPS 2023
Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
NeurIPS 2023
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
NeurIPS 2023
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
ICML 2022
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
ICLR 2022
On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization
IJCAI 2021