Molei Tao
26 papers · 2020–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (10) 🏃 Academic Marathon (5)
🗺️
Taxonomy Completionist
(10)
🧭
Keyword Pioneer
🏆
Keyword Champion
(2)
👑
Triple Crown
🗃️
Keyword Collector
(95)
⚡
Prolific Year
(6)
💎
Century Club
(26)
🔥
Unstoppable
(6)
❓
The Questioner
Conferences
NIPS (9)
ICLR (7)
AISTATS (3)
ICML (3)
ALT (1)
COLT (1)
JMLR (1)
WACV (1)
Top co-authors
Keywords
convergence rate
(4)
diffusion model
(4)
markov chain monte carlo
(3)
lie group
(3)
nonconvex optimization
(2)
nesterov accelerated gradient
(2)
convex optimization
(2)
generative model
(2)
gradient descent
(2)
learning rate
(2)
convergence analysis
(1)
constrained generation
(1)
optimal transport
(1)
deep learning theory
(1)
image generation
(1)
langevin dynamics
(1)
matrix factorization
(1)
diffusion process
(1)
variational inequality
(1)
stochastic gradient descent
(1)
Papers
Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
ICML 2025
Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
ICLR 2025
Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
ICLR 2025
SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models
WACV 2025
Variational Schrödinger Momentum Diffusion
AISTATS 2025
Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images
ICLR 2025
Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult
JMLR 2025
Convergence of Kinetic Langevin Monte Carlo on Lie groups
COLT 2024
Evaluating the design space of diffusion-based generative models
NIPS 2024
Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
NIPS 2024
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
NIPS 2024
Quantitative Convergences of Lie Group Momentum Optimizers
NIPS 2024
Extragradient Type Methods for Riemannian Variational Inequality Problems
AISTATS 2024
Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport
ICLR 2023
gDDIM: Generalized denoising diffusion implicit models
ICLR 2023
Deep Momentum Multi-Marginal Schrödinger Bridge
NIPS 2023
Mirror Diffusion Models for Constrained and Watermarked Generation
NIPS 2023
Sqrt(d) Dimension Dependence of Langevin Monte Carlo
ICLR 2022
Hessian-Free High-Resolution Nesterov Acceleration For Sampling
ICML 2022
Alternating Mirror Descent for Constrained Min-Max Games
NIPS 2022
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect
ICLR 2022
The Mirror Langevin Algorithm Converges with Vanishing Bias
ALT 2022
Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps
ICML 2021
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective
NIPS 2020
Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue Problems
AISTATS 2020
Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function
NIPS 2020