Runzhe Wang
6 papers · 2021–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
deep reinforcement learning
(1)
stochastic gradient descent
(1)
sample efficiency
(1)
robustness
(1)
mathematical reasoning
(1)
neural network optimization
(1)
gradient descent
(1)
margin maximization
(1)
low-rank matrix
(1)
linear classifier
(1)
learning rate
(1)
diffusion model
(1)
bandit optimization
(1)
zeroth-order optimization
(1)
score-based diffusion
(1)
neural network approximation
(1)
two-layer neural network
(1)
global structure
(1)
denoising network
(1)
large language model
(1)
Papers
MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations
ICML 2025
Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
ICLR 2025
The Marginal Value of Momentum for Small Learning Rate SGD
ICLR 2024
Going Beyond Linear RL: Sample Efficient Neural Function Approximation
NeurIPS 2021
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
NeurIPS 2021
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
NeurIPS 2021