Zhengmian Hu
21 papers · 2021–2025 · 7 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 ↓+7 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (51) π€ Dynamic Duo (16)
π
Triple Crown
π
Grand Slam
π¬
Deep Specialist
(10)
π₯
Mega-Team Β· Squad
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(118)
Top co-authors
Research topics
Machine Learning
(17)
Optimization & Theory Β· Machine Learning
(15)
Deep Learning
(8)
Artificial Intelligence
(7)
Mathematics & Optimization
(6)
Natural Language Processing
(6)
Optimization
(6)
Core AI
(5)
Learning Types Β· Machine Learning
(5)
Optimization & Theory Β· Deep Learning
(4)
Core Methods
(3)
Generation
(3)
Learning Types Β· Deep Learning
(3)
Application Areas
(2)
Architectures
(2)
Keywords
large language model
(6)
non-convex optimization
(4)
minimax optimization
(4)
sample complexity
(3)
gradient complexity
(3)
stochastic gradient descent
(3)
federated learning
(3)
variance reduction
(3)
stochastic gradient
(2)
communication efficiency
(2)
speculative sampling
(2)
bayesian inference
(1)
neural tangent kernel
(1)
policy gradient
(1)
convex optimization
(1)
robustness
(1)
one-shot learning
(1)
bayesian learning
(1)
deep learning theory
(1)
active learning
(1)
Papers
Cautious Next Token Prediction
ACL 2025
From Selection to Generation: A Survey of LLM-based Active Learning
ACL 2025
GUI Agents: A Survey
ACL 2025
Towards Optimal Multi-draft Speculative Decoding
ICLR 2025
A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution
EMNLP 2024
Accelerated Speculative Sampling Based on Tree Monte Carlo
ICML 2024
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
ICML 2024
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
NeurIPS 2024
Robust Reinforcement Learning with General Utility
NeurIPS 2024
Unbiased Watermark for Large Language Models
ICLR 2024
AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization
AISTATS 2023
Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization
ICML 2023
Decentralized Riemannian Algorithm for Nonconvex Minimax Problems
AAAI 2023
Faster Adaptive Federated Learning
AAAI 2023
Federated Conditional Stochastic Optimization
NeurIPS 2023
Optimization and Bayes: A Trade-off for Overparameterized Neural Networks
NeurIPS 2023
Solving a Class of Non-Convex Minimax Optimization in Federated Learning
NeurIPS 2023
Tighter Analysis for ProxSkip
ICML 2023
Fast and Scalable Adversarial Training of Kernel SVM via Doubly Stochastic Gradients
AAAI 2021
On the Random Conjugate Kernel and Neural Tangent Kernel
ICML 2021
Optimal Underdamped Langevin MCMC Method
NeurIPS 2021