Rongzhen Wang
4 papers · 2024–2026 · 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
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
learning theory
(1)
autoregressive transformer
(1)
hyperparameter optimization
(1)
in-context learning
(1)
preference optimization
(1)
stability analysis
(1)
gradient descent
(1)
variance reduction
(1)
bilevel optimization
(1)
lower bound
(1)
gradient-based algorithm
(1)
autoregressive training
(1)
self-attention model
(1)
least square
(1)
antithetic sampling
(1)
conditional generative modeling
(1)
uniform stability
(1)
multi-source training
(1)
score estimator
(1)
convergence dynamics
(1)
Papers
LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
ACL 2026
A Theory for Conditional Generative Modeling on Multiple Data Sources
ICML 2025
Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
NeurIPS 2024
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
NeurIPS 2024