* I publish under the name Haoze Wu

Preprints/In-preparation

Publications

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
Haoze Wu, Omri Isac, Aleksandar Zeljić, Teruhiro Tagomori, Matthew Daggitt, Wen Kokke, Idan Refaeli, Guy Amir, Kyle Julian, Shahaf Bassan, Pei Huang, Ori Lahav, Min Wu, Min Zhang, Ekaterina Komendantskaya, Guy Katz, Clark Barrett
International Conference on Computer Aided Verification (CAV'24)

Lemur: Integrating Large Language Models in Automated Program Verification
Haoze Wu, Clark Barrett, Nina Narodytska
International Conference on Learning Representations (ICLR'24)

VeriX: Towards Verified Explainability of Deep Neural Networks
Min Wu, Haoze Wu, Clark Barrett
Advances in neural information processing systems (NeurIPS'23)

Lightweight Online Learning for Sets of Related Problems in Automated Reasoning
Haoze Wu, Christopher Hahn, Florian Lonsing, Makai Mann, Raghuram Ramanujan, Clark Barrett
Formal Methods in Computer-Aided Design (FMCAD'23) (Best paper nominee)

Soy: An Efficient MILP Solver for Piecewise-Affine Systems
Haoze Wu, Min Wu, Dorsa Sadigh, Clark Barrett
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'23)

Convex Bounds on the Softmax Function with Applications to Robustness Verification
Dennis Wei, Haoze Wu, Min Wu, Pin-Yu Chen, Clark Barrett, Eitan Farchi
International Conference on Artificial Intelligence and Statistics (AISTATS'23)

Toward Certified Robustness against Real-World Distribution Shifts
Haoze Wu*, Teruhiro Tagomori*, Alexander Robey*, Fengjun Yang*, Nikolai Matni, George Pappas, Hamed Hassani, Corina Pasareanu, Clark Barrett
2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML'23)

* denotes equal contribution.

Scalable Verification of GNN-based Job Schedulers
Haoze Wu, Clark Barrett, Mahmood Sharif, Nina Narodytska, Gagandeep Singh
Proceedings of the ACM on Programming Languages (OOPSLA'22)

Proof-Stitch: Proof Combination for Divide-and-Conquer SAT Solvers
Abhishek Nair, Saranyu Chattopadhyay, Haoze Wu, Alex Ozdemir, Clark Barrett
Formal Methods in Computer-Aided Design (FMCAD'22)

On Optimizing Back-Substitution Methods for Neural Network Verification
Tom Zelazny, Haoze Wu, Clark Barrett, Guy Katz
Formal Methods in Computer-Aided Design (FMCAD'22)

Efficient Neural Network Analysis with Sum-of-Infeasibilities
Haoze Wu, Aleksandar Zeljic, Guy Katz, Clark Barrett
Tools and Algorithms for the Construction and Analysis of Systems (TACAS'22)

Global Optimization of Objective Functions Represented by ReLU Networks
Christopher A. Strong, Haoze Wu, Aleksandar Zeljić, Kyle D. Julian, Guy Katz, Clark Barrett, Mykel J. Kochenderfer
Journal of Machine Learning

SAT-Solving in the Serverless Cloud
Alex Ozdemir*, Haoze Wu*, Clark Barrett
Formal Methods in Computer Aided Design (FMCAD'21)

* denotes equal contribution.

An SMT-Based Approach for Verifying Binarized Neural Networks
Guy Amir, Haoze Wu, Clark Barrett, Guy Katz
Tools and Algorithms for the Construction and Analysis of Systems (TACAS'21)

DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifiers
Colin Paterson, Haoze Wu, John Grese, Radu Calinescu, Corina S. Pasareanu, Clark Barrett
International Conference on Computer Safety, Reliability and Security (SafeComp'21)

Towards Verification of Neural Networks for Small Unmanned Aircraft Collision Avoidance
Ahmed Irfan, Kyle D. Julian, Haoze Wu, Clark Barrett, Mykel J. Kochenderfer, Baoluo Meng, and James Lopez.
2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC'20)

Parallelization Techniques for Verifying Neural Networks
Haoze Wu, Alex Ozdemir, Aleksandar Zeljić, Ahmed Irfan, Kyle Julian, Divya Gopinath, Sadjad Fouladi, Guy Katz, Corina Pasareanu, Clark Barrett
2020 Formal Methods in Computer Aided Design (FMCAD'20)

G2SAT: Learning to Generate SAT Formulas
Jiaxuan You*, Haoze Wu*, Clark Barrett, Raghuram Ramanujan, Jure Leskovec
Advances in neural information processing systems (NeurIPS'19)

* denotes equal contribution.

Learning to Generate Industrial SAT Instances
Haoze Wu, Raghuram Ramanujan
Twelfth Annual Symposium on Combinatorial Search (SoCS'19)

The Marabou Framework for Verification and Analysis of Deep Neural Networks
Guy Katz, Derek A Huang, Duligur Ibeling, Kyle Julian, Christopher Lazarus, Rachel Lim, Parth Shah, Shantanu Thakoor, Haoze Wu, Aleksandar Zeljić, David L Dill, Mykel J Kochenderfer, Clark Barrett
International Conference on Computer Aided Verification (CAV'19)

Improving SAT-solving with Machine Learning
Haoze Wu
ACM SIGCSE Technical Symposium on Computer Science Education (Student Research Competition)