Scholar
Alan Zhu
Google Scholar ID: Xh0VtVUAAAAJ
PhD Student; University of California, Berkeley
Citations & Impact
Citations
263
H-index
4
i10-index
2
Publications
6
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 1. Conference Publication: 'Accelerating Retrieval-augmented Language Model Serving with Speculation', ICML 2024
- 2. Conference Publication: 'SpecInfer: Accelerating Generative Large Language Model Serving with Speculative Inference and Token Tree Verification', ASPLOS 2024
- 3. Conference Publication: 'Robotic Metamaterials', CHI 2024
- 4. Preprint and Workshop Presentation: 'How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models', NeurIPS FoRLM Workshop 2025
- 5. Preprint: 'Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First', 2025
- 6. Preprint: 'BARE: Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation', ICML DataWorld Workshop Oral 2025
- 7. Preprint: 'Efficient Estimation of Shortest-Path Distance Distributions to Samples in Graphs', 2025
Research Experience
- 1. Worked in Catalyst Lab at Carnegie Mellon University, supervised by Prof. Zhihao Jia
- 2. Worked in Interactive Structures Lab at Carnegie Mellon University, supervised by Prof. Alexandra Ion
- 3. Conducted research at the University of Michigan, supervised by Prof. Qiaozhu Mei
- 4. TA for 15-251 Great Ideas in Theoretical Computer Science at Carnegie Mellon University (Fall 2021 - Spring 2024)
Education
- 1. PhD, University of California, Berkeley, Computer Science, Advisor: Prof. Joseph Gonzalez (2022-present)
- 2. BS, Carnegie Mellon University, Major in Computer Science with an additional major in Mathematical Statistics, worked in Catalyst Lab under Prof. Zhihao Jia and in Interactive Structures Lab under Prof. Alexandra Ion (time not specified)
Background
- Research interests: Improving the personalization and specialization of AI systems, especially in data-scarce settings and by leveraging non-scalar feedback. Currently a CS PhD student at UC Berkeley, advised by Prof. Joseph Gonzalez. Supported by an NSF Graduate Research Fellowship.
Miscellany
- In high school, active in math and robotics competitions. Qualified for USAJMO (2016) and USAMO (2019). Served as programming team lead for the robotics team (FRC Team #5530 - The Greenhills Lawnmowers), which qualified for the FIRST World Championships in 2019.
Co-authors