Banghua Zhu
16 papers · 2021–2025 · 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (33) ποΈ Keyword Collector (81)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(7)
Top co-authors
Research topics
Artificial Intelligence
(13)
Machine Learning
(12)
Core AI
(10)
Optimization & Theory
(8)
Reinforcement Learning
(4)
Learning Types
(4)
Natural Language Processing
(3)
Learning Paradigms
(3)
Methods
(3)
Mathematics & Optimization
(2)
Application Areas
(2)
Resources & Methods
(2)
Computer Science
(1)
Computer Vision
(1)
Deep Learning
(1)
Keywords
reward model
(4)
sample complexity
(4)
reinforcement learning
(3)
large language model
(3)
policy learning
(2)
reinforcement learning from human feedback
(2)
kullback-leibler divergence
(2)
pairwise comparison
(2)
imitation learning
(2)
human preference
(2)
offline reinforcement learning
(1)
object detection
(1)
knowledge transfer
(1)
robust statistics
(1)
function approximation
(1)
reward modeling
(1)
game theory
(1)
deep learning
(1)
semi-supervised learning
(1)
autonomous driving
(1)
Papers
From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline
ICML 2025
How to Evaluate Reward Models for RLHF
ICLR 2025
Noisy Computing of the Threshold Function
ALT 2025
Taming Overconfidence in LLMs: Reward Calibration in RLHF
ICLR 2025
Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
ICML 2024
Fairness in Serving Large Language Models
OSDI 2024
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
ICML 2024
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
ICLR 2024
Towards the Fundamental Limits of Knowledge Transfer over Finite Domains
ICLR 2024
Byzantine-Robust Federated Learning with Optimal Statistical Rates
AISTATS 2023
Doubly-Robust Self-Training
NeurIPS 2023
Jump-Start Reinforcement Learning
ICML 2023
Online Learning in Stackelberg Games with an Omniscient Follower
ICML 2023
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
ICML 2023
Towards Optimal Caching and Model Selection for Large Model Inference
NeurIPS 2023
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
NeurIPS 2021