Bio

My research focuses on developing trustworthy machine learning, with an emphasis on methods that interpret and explain the complex decision-making processes of foundation models, using techniques from signal processing and game theory.

I am a fourth year Ph.D. student in EECS at Berkeley, advised by Kannan Ramchandran. I am an NSF Graduate Research Fellow and have interned with Apple and Uber AI.

Publications

ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
ArXiv, 2025
Landon Butler*, Abhineet Agarwal*, Justin Singh Kang*, Yigit Efe Erginbas, Kannan Ramchandran, and Bin Yu
SPEX: Scaling Feature Interaction Explanations for LLMs
ICML, 2025
Justin Singh Kang*, Landon Butler*, Abhineet Agarwal*, Yigit Efe Erginbas, Kannan Ramchandran, and Bin Yu
Learning to Understand: Identifying Interactions via the Möbius Transform
NeurIPS, 2024
Justin Singh Kang, Yigit Efe Erginbas, Landon Butler, Ramtin Pedarsani, and Kannan Ramchandran
Convolutional Learning on Multigraphs
IEEE Transactions on Signal Processing, 2023
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
Landon Butler, Alejandro Parada-Mayorga, and Alejandro Ribeiro
Convolutional Filtering and Neural Networks with Non-Commutative Algebras
IEEE Transactions on Signal Processing, 2023
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024
Alejandro Parada-Mayorga, Landon Butler, and Alejandro Ribeiro
Equitable Optimization of U.S. Airline Route Networks
Computers, Environment and Urban Systems, 2023
Andrew P. Sage Memorial Conference, 2022
Arnav Joshi, Andy Eskenazi, Landon Butler, and Megan Ryerson
Best Paper Award in Climate and Transportation (Sage)
Democratizing Aviation Emissions Estimation: Development of an Open-Source, Data-Driven Methodology
International Conference on Research in Air Transportation (ICRAT), 2022
Andy Eskenazi, Landon Butler, Arnav Joshi, and Megan Ryerson
Best Paper Award in Economics, Policy, and Equity
Learning Connectivity for Data Distribution in Robot Teams
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Ekaterina Tolstaya, Landon Butler, Daniel Mox, James Paulos, Vijay Kumar, and Alejandro Ribeiro