Jack Xin
3 papers · 2019–2025 · 1 venue · 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 ↓
🏃
Academic Marathon · Sprint
Venues
Top co-authors
Research topics
Keywords
convergence analysis
(1)
gradient descent
(1)
expressive power
(1)
equivariant graph neural network
(1)
binarized neural network
(1)
straight-through estimator
(1)
score-based generative model
(1)
activation quantization
(1)
3d geometric structure
(1)
coarse gradient
(1)
steerable feature
(1)
irreducible decomposition
(1)
lipschitz estimate
(1)
global well-posedness
(1)
numerical scheme
(1)
Papers
Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates
ICLR 2025
Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
ICLR 2024
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
ICLR 2019