Runzhe Wang
6 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(14)
Conferences
NIPS (3)
ICLR (2)
ICML (1)
Top co-authors
Keywords
deep reinforcement learning
(1)
sample efficiency
(1)
gradient descent
(1)
margin maximization
(1)
low-rank matrix
(1)
linear classifier
(1)
bandit optimization
(1)
zeroth-order optimization
(1)
neural network approximation
(1)
two-layer neural network
(1)
neural function approximation
(1)
nonlinear reinforcement learning
(1)
non-concave reward
(1)
neural network bandit
(1)
Papers
Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
ICLR 2025
MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations
ICML 2025
The Marginal Value of Momentum for Small Learning Rate SGD
ICLR 2024
Going Beyond Linear RL: Sample Efficient Neural Function Approximation
NIPS 2021
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
NIPS 2021
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
NIPS 2021