Sotabase

Career

· PhD Student, UC Berkeley EECS Department2024–
· Research Intern, UC Berkeley EECS Department2023–2023
· Researcher, UC Berkeley Robotics2022–

Publications (41)

Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
International Conference on Machine Learning · 2024
1,012
cited
From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
International Conference on Machine Learning · 2024
346
cited
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
IEEE Transactions on Information Theory · 2021
316
cited
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
International Conference on Machine Learning · 2023
254
cited
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
arXiv.org · 2023
146
cited
Jump-Start Reinforcement Learning
International Conference on Machine Learning · 2022
145
cited
Joint Transceiver Optimization for Wireless Communication PHY Using Neural Network
IEEE Journal on Selected Areas in Communications · 2019
102
cited
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
arXiv.org · 2023
71
cited
The Sample Complexity of Online Contract Design
ACM Conference on Economics and Computation · 2022
61
cited
Deconstructing Generative Adversarial Networks
IEEE Transactions on Information Theory · 2019
53
cited
Generalized Resilience and Robust Statistics
Annals of Statistics · 2019
53
cited
Fine-Tuning Language Models with Advantage-Induced Policy Alignment
arXiv.org · 2023
49
cited
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
International Conference on Machine Learning · 2024
47
cited
Robust estimation via generalized quasi-gradients
Information and Inference A Journal of the IMA · 2020
43
cited
Byzantine-Robust Federated Learning with Optimal Statistical Rates
International Conference on Artificial Intelligence and Statistics · 2022
41
cited
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
arXiv.org · 2025
33
cited
On Optimal Caching and Model Multiplexing for Large Model Inference
arXiv.org · 2023
28
cited
SLoRA: Scalable Serving of Thousands of LoRA Adapters
Conference on Machine Learning and Systems · 2024
27
cited
Sparse Tensor Decomposition for Haplotype Assembly of Diploids and Polyploids
BMC Genomics · 2017
27
cited
Towards Optimal Statistical Watermarking
arXiv.org · 2023
23
cited
Sotabase
Banghua Zhu | Researcher Profile | Sotabase | Sotabase