Michael Luo

25 papers A* 6Misc 1Journal 15Unranked 3
YearRankTypeTitle / Venue / Authors
2025 J jnl
Autellix: An Efficient Serving Engine for LLM Agents as General Programs.
CoRR
Michael Luo, Xiaoxiang Shi, Colin Cai, Tianjun Zhang, Justin Wong, Yichuan Wang, Chi Wang, Yanping Huang, Zhifeng Chen, Joseph E. Gonzalez, Ion Stoica
2025 J jnl
WorldModelBench: Judging Video Generation Models As World Models.
CoRR
Dacheng Li, Yunhao Fang, Yukang Chen, Shuo Yang, Shiyi Cao, Justin Wong, Michael Luo, Xiaolong Wang, Hongxu Yin, Joseph E. Gonzalez, Ion Stoica, Song Han, Yao Lu
2024 J jnl
SimpleStrat: Diversifying Language Model Generation with Stratification.
CoRR
Justin Wong, Yury Orlovskiy, Michael Luo, Sanjit A. Seshia, Joseph E. Gonzalez
2024 — conf
Starburst: A Cost-aware Scheduler for Hybrid Cloud.
USENIX ATC
Michael Luo, Siyuan Zhuang, Suryaprakash Vengadesan, Romil Bhardwaj, Justin Chang, Eric J. Friedman, Scott Shenker, Ion Stoica
2024 A* conf
Stylus: Automatic Adapter Selection for Diffusion Models.
NeurIPS
Michael Luo, Justin Wong, Brandon Trabucco, Yanping Huang, Joseph E. Gonzalez, Zhifeng Chen, Ruslan Salakhutdinov, Ion Stoica
2024 J jnl
Stylus: Automatic Adapter Selection for Diffusion Models.
CoRR
Michael Luo, Justin Wong, Brandon Trabucco, Yanping Huang, Joseph E. Gonzalez, Zhifeng Chen, Ruslan Salakhutdinov, Ion Stoica
2023 Misc conf
SkyPilot: An Intercloud Broker for Sky Computing.
NSDI
Zongheng Yang, Zhanghao Wu, Michael Luo, Wei-Lin Chiang, Romil Bhardwaj, Woosuk Kwon, Siyuan Zhuang, Frank Sifei Luan, Gautam Mittal, Scott Shenker, Ion Stoica
2022 — conf
Balsa: Learning a Query Optimizer Without Expert Demonstrations.
SIGMOD Conference
Zongheng Yang, Wei-Lin Chiang, Sifei Luan, Gautam Mittal, Michael Luo, Ion Stoica
2022 J jnl
Balsa: Learning a Query Optimizer Without Expert Demonstrations.
CoRR
Zongheng Yang, Wei-Lin Chiang, Sifei Luan, Gautam Mittal, Michael Luo, Ion Stoica
2021 A* conf
Accelerating Quadratic Optimization with Reinforcement Learning.
NeurIPS
Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato, Goran Banjac, Michael Luo, Francesco Borrelli, Joseph E. Gonzalez, Ion Stoica, Ken Goldberg
2021 J jnl
Accelerating Quadratic Optimization with Reinforcement Learning.
CoRR
Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato, Goran Banjac, Michael Luo, Francesco Borrelli, Joseph E. Gonzalez, Ion Stoica, Ken Goldberg
2021 A* conf
Discovering Non-monotonic Autoregressive Orderings with Variational Inference.
ICLR
Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao
2021 J jnl
Discovering Non-monotonic Autoregressive Orderings with Variational Inference.
CoRR
Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao
2021 — conf
LazyDAgger: Reducing Context Switching in Interactive Imitation Learning.
CASE
Ryan Hoque, Ashwin Balakrishna, Carl Putterman, Michael Luo, Daniel S. Brown, Daniel Seita, Brijen Thananjeyan, Ellen R. Novoseller, Ken Goldberg
2021 J jnl
LazyDAgger: Reducing Context Switching in Interactive Imitation Learning.
CoRR
Ryan Hoque, Ashwin Balakrishna, Carl Putterman, Michael Luo, Daniel S. Brown, Daniel Seita, Brijen Thananjeyan, Ellen R. Novoseller, Ken Goldberg
2021 A* conf
Learning Seed Placements and Automation Policies for Polyculture Farming with Companion Plants.
ICRA
Yahav Avigal, Anna Deza, William Wong, Sebastian Oehme, Mark Presten, Mark Theis, Jackson Chui, Paul Shao, Huang Huang, Atsunobu Kotani, Satvik Sharma, Rishi Parikh, Michael Luo, Sandeep Mukherjee, Stefano Carpin, Joshua H. Viers, Stavros Vougioukas, Ken Goldberg
2021 J jnl
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance.
CoRR
Michael Luo, Ashwin Balakrishna, Brijen Thananjeyan, Suraj Nair, Julian Ibarz, Jie Tan, Chelsea Finn, Ion Stoica, Ken Goldberg
2021 A* conf
RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem.
NeurIPS
Eric Liang, Zhanghao Wu, Michael Luo, Sven Mika, Joseph E. Gonzalez, Ion Stoica
2021 J jnl
Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.
IEEE Robotics Autom. Lett.
Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair, Michael Luo, Krishnan Srinivasan, Minho Hwang, Joseph E. Gonzalez, Julian Ibarz, Chelsea Finn, Ken Goldberg
2020 J jnl
Context-Conditioning as Cognitive Control: Guiding Meta-learning with Task Information.
CoRR
Rachit Dubey, Erin Grant, Michael Luo, Karthik Narasimhan, Thomas L. Griffiths
2020 J jnl
Distributed Reinforcement Learning is a Dataflow Problem.
CoRR
Eric Liang, Zhanghao Wu, Michael Luo, Sven Mika, Ion Stoica
2020 A* conf
IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks.
ICLR
Michael Luo, Jiahao Yao, Richard Liaw, Eric Liang, Ion Stoica
2020 J jnl
Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones.
CoRR
Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair, Michael Luo, Krishnan Srinivasan, Minho Hwang, Joseph E. Gonzalez, Julian Ibarz, Chelsea Finn, Ken Goldberg
2019 J jnl
IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks.
CoRR
Michael Luo, Jiahao Yao, Richard Liaw, Eric Liang, Ion Stoica
2014 J jnl
Clinical, functional, and radiographic outcomes following total knee arthroplasty with patient-specific instrumentation, computer-assisted surgery, and manual instrumentation: a short-term follow-up study.
Int. J. Comput. Assist. Radiol. Surg.
Mark Yaffe, Michael Luo, Nitin Goyal, Philip Chan, Anay Patel, Max Cayo, S. David Stulberg