Sotabase

Career

· Leadership Team, Stealth Startup2024–
· Software Engineer Intern, Anyscale2020–2020
· Graduate Student Researcher, Berkeley RISE Lab2019–2024
· Teaching Assistant, University of Science and Technology of China2016–2017

Publications (28)

Judging LLM-as-a-judge with MT-Bench and Chatbot Arena
Neural Information Processing Systems · 2023
6,903
cited
Efficient Memory Management for Large Language Model Serving with PagedAttention
Symposium on Operating Systems Principles · 2023
4,514
cited
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
International Conference on Learning Representations · 2023
346
cited
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
International Conference on Machine Learning · 2021
155
cited
SkyPilot: An Intercloud Broker for Sky Computing
Symposium on Networked Systems Design and Implementation · 2023
99
cited
Hoplite: efficient and fault-tolerant collective communication for task-based distributed systems
Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication · 2020
28
cited
This paper is included in the Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation.
28
cited
HuatuoGPT, Towards Taming Language Models To Be a Doctor
21
cited
sensAI: ConvNets Decomposition via Class Parallelism for Fast Inference on Live Data
Conference on Machine Learning and Systems · 2021
12
cited
Composing MPC With LQR and Neural Network for Amortized Efficiency and Stable Control
IEEE Transactions on Automation Science and Engineering · 2021
10
cited
Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment
Volume 1 · 2024
6
cited
Rearchitecting In-Memory Object Stores for Low Latency
Proceedings of the VLDB Endowment · 2021
5
cited
Starburst: A Cost-aware Scheduler for Hybrid Cloud
USENIX Annual Technical Conference · 2024
5
cited
Composing MPC with LQR and Neural Networks for Efficient and Stable Control
arXiv.org · 2021
2
cited
From KMMLU-Redux to Pro: A Professional Korean Benchmark Suite for LLM Evaluation
Conference on Empirical Methods in Natural Language Processing · 2025
2
cited
2025 RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
A Statistical Framework for Ranking LLM-Based Chatbots
2024
Bearing run-to-failure datasets of UNSW
2021
B ENCH : Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions
Budget-aware Test-time Scaling via Discriminative Verification
2025
Sotabase
Siyuan Zhuang | Researcher Profile | Sotabase | Sotabase