Gonzalez Group Photo Collage

Gonzalez Group

Enthusiastically Advancing AI Systems at UC Berkeley

Joseph E. Gonzalez

Joey Gonzalez's group at UC Berkeley focuses on advancing AI systems, including LLM Agents, data systems, efficent ML training and inference, and generative model evaluation. His group has spawned many successful projects such as Gorilla, Chatbot Arena, vLLM, MemGPT (now Letta), SGLang and more.
Visit the Google Scholar page for more our current publications. His students also have a podcast on PhD life here.

Locality-aware Fair Scheduling in LLM Serving

Shiyi Cao and Yichuan Wang and Ziming Mao and Pin-Lun Hsu and Liangsheng Yin and Tian Xia and Dacheng Li and Shu Liu and Yineng Zhang and Yang Zhou and Ying Sheng and Joseph Gonzalez and Ion Stoica

arXiv preprint arXiv:2501.14312

BARE: Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation

Alan Zhu and Parth Asawa and Jared Quincy Davis and Lingjiao Chen and Ion Stoica and Joseph E Gonzalez and Matei Zaharia

arXiv preprint arXiv:2502.01697

Adaptive Semantic Prompt Caching with VectorQ

Luis Gaspar Schroeder and Shu Liu and Alejandro Cuadron and Mark Zhao and Stephan Krusche and Alfons Kemper and Matei Zaharia and Joseph E Gonzalez

arXiv preprint arXiv:2502.03771

See Say and Segment: Teaching LMMs to Overcome False Premises

Tsung-Han Wu and Giscard Biamby and David Chan and Lisa Dunlap and Ritwik Gupta and Xudong Wang and Joseph E Gonzalez and Trevor Darrell

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models

Lisa Dunlap and Krishna Mandal and Trevor Darrell and Jacob Steinhardt and Joseph E Gonzalez

arXiv preprint arXiv:2410.12851

GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications

Shishir G Patil and Tianjun Zhang and Vivian Fang and Roy Huang and Aaron Hao and Martin Casado and Joseph E Gonzalez and Raluca Ada Popa and Ion Stoica

arXiv preprint arXiv:2404.06921

How to Evaluate Reward Models for RLHF

Evan Frick and Tianle Li and Connor Chen and Wei-Lin Chiang and Anastasios N Angelopoulos and Jiantao Jiao and Banghua Zhu and Joseph E Gonzalez and Ion Stoica

arXiv preprint arXiv:2410.14872

Fairness in serving large language models

Ying Sheng and Shiyi Cao and Dacheng Li and Banghua Zhu and Zhuohan Li and Danyang Zhuo and Joseph E Gonzalez and Ion Stoica

18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)

Investigating the behavior of diffusion models for accelerating electronic structure calculations

Daniel Rothchild and Andrew S Rosen and Eric Taw and Connie Robinson and Joseph E Gonzalez and Aditi S Krishnapriyan

Chemical Science