Research
In Progress
Stability guarantees + Boolean analysis + LLMs.
Mathematically-backed explanations + feature bias in big models.
Learning in-context learning.
I am a contributor to the Transformer Cookbook.
I am a developer on BrachioLab’s exlib.
Preprints
Probabilistic Stability Guarantees for Feature Attributions
Helen Jin*, Anton Xue*, Weiqiu You, Surbhi Goel, Eric Wong
In submission
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
Thomas T. Zhang*, Behrad Moniri*, Ansh Nagwekar, Faraz Rahman, Anton Xue, Hamed Hassani, Nikolai Matni
In submission
The FIX Benchmark: Extracting Features Interpretable to eXperts
Helen Jin, Shreya Havaldar, Chaehyeon Kim, Anton Xue, Weiqiu You, Helen Qu, Marco Gatti, Daniel A Hashimoto, Bhuvnesh Jain, Amin Madani, Masao Sako, Lyle Ungar, Eric Wong
In submission, [GitHub]
Publications
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
Anton Xue*, Avishree Khare*, Rajeev Alur, Surbhi Goel, Eric Wong
ICLR 2025, [GitHub], [Blog post]
AR-Pro: Anomaly Explanation and Repair with Formal Properties
Xiayan Ji*, Anton Xue*, Eric Wong, Oleg Sokolsky, Insup Lee
NeurIPS 2024
TYGR: Type Inference on Stripped Binaries using Graph Neural Networks
Chang Zhu, Ziyang Li, Anton Xue, Ati Priya Bajaj, William Gibbs, Yibo Liu, Rajeev Alur, Tiffany Bao, Hanjun Dai, Adam Doupé, Mayur Naik, Yan Shoshitaishvili, Ruoyu Wang, and Aravind Machiry
USENIX Security 2024
Chordal Sparsity for SDP-Based Neural Network Verification
Anton Xue, Lars Lindemann, and Rajeev Alur
Automatica 2024, [GitHub]
Stability Guarantees for Feature Attributions with Multiplicative Smoothing
Anton Xue, Rajeev Alur, and Eric Wong
NeurIPS 2023, [GitHub], [Blog post]
Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
Anton Xue, Lars Lindemann, Alexander Robey, Hamed Hassani, George Pappas, and Rajeev Alur
CDC 2022, [GitHub]
Synchronization Schemas
Rajeev Alur, Phillip Hilliard, Zachary Ives, Konstantinos Kallas, Konstantinos Mamouras, Filip Niksic, Caleb Stanford, Val Tannen, and Anton Xue
Principles of Database Systems 2021
Safe Reinforcement Learning via Statistical Model Predictive Shielding
Osbert Bastani, Shuo Li, Anton Xue
RSS 2021
Data-Driven System Level Synthesis
Anton Xue and Nikolai Matni
L4DC 2021, [GitHub]
A Self-certifying Compilation Framework for WebAssembly
Kedar Namjoshi and Anton Xue
VMCAI 2021, [GitHub]
G2Q: Haskell Constraint Solving
William Hallahan, Anton Xue, and Ruzica Piskac
Haskell Symposium 2019
Lazy Counterfactual Symbolic Execution
William Hallahan, Anton Xue, Maxwell Bland, Ranjit Jhala, and Ruzica Piskac
PLDI 2019, [GitHub], [Video Abstract]