Haochuan Li
10 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π Conference Polyglot (4) π Academic Marathon (6) π Cross-Pollinator (12)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(19)
π§
Keyword Pioneer
π
Century Club
(10)
Conferences
NIPS (5)
ICML (3)
CVPR (1)
ICLR (1)
Top co-authors
Keywords
gradient descent
(4)
stationary point
(3)
neural network optimization
(2)
convergence analysis
(2)
stochastic optimization
(2)
minimax optimization
(2)
deep neural network
(2)
convergence rate
(2)
non-convex optimization
(2)
iterative refinement
(1)
text-to-image generation
(1)
nonconvex optimization
(1)
neural tangent kernel
(1)
adversarial training
(1)
robust optimization
(1)
dynamical system
(1)
convergence guarantee
(1)
global convergence
(1)
gradient descent optimization
(1)
direct preference optimization
(1)
Papers
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
CVPR 2025
TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
ICLR 2025
Convergence of Adam Under Relaxed Assumptions
NIPS 2023
Convex and Non-convex Optimization Under Generalized Smoothness
NIPS 2023
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective
ICML 2022
Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems
NIPS 2022
On Convergence of Gradient Descent Ascent: A Tight Local Analysis
ICML 2022
Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization
NIPS 2021
Gradient Descent Finds Global Minima of Deep Neural Networks
ICML 2019
Convergence of Adversarial Training in Overparametrized Neural Networks
NIPS 2019