Donghao Li
8 papers · 2020–2026 · 6 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 ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (24) π£ Hot Topic Early Bird π Conference Polyglot Β· Silver
π
Renaissance Researcher
(5)
π
Trend Setter
Top co-authors
Research topics
Machine Learning
(7)
Deep Learning
(3)
Core Methods
(3)
Learning Types
(3)
Optimization & Theory
(3)
Artificial Intelligence
(2)
Reinforcement Learning
(2)
Application Areas
(2)
Core AI
(2)
Methods
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Security & Privacy
(1)
Architectures
(1)
Generation
(1)
Keywords
reinforcement learning
(2)
differential privacy
(1)
stochastic approximation
(1)
sample complexity
(1)
feature learning
(1)
offline reinforcement learning
(1)
online learning
(1)
data augmentation
(1)
convergence rate
(1)
text-to-image generation
(1)
deep learning
(1)
reinforcement learning from human feedback
(1)
markov decision process
(1)
regret minimization
(1)
privacy attack
(1)
curse of dimensionality
(1)
regret bound
(1)
diffusion model
(1)
federated learning
(1)
model compression
(1)
Papers
PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
CVPR 2026
A Shared Low-Rank Adaptation Approach to Personalized RLHF
AISTATS 2025
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
UAI 2025
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
CVPR 2025
PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
ACL 2024
Random Smoothing Regularization in Kernel Gradient Descent Learning
JMLR 2024
Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints
ICML 2023
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
ICML 2020