SAIV 2024

Program

# Main Room
9:00

Verified Autonomy with Neural Lyapunov Barrier Certificates

Clark Barrett

Keynote 

:30
10:00

Chronosymbolic Learning: Efficient CHC Solving with Symbolic Reasoning and Inductive Learning

Ziyan Luo, Xujie Si

Paper 

:30

Coffee break

11:00

Provable Preimage Under-Approximation for Neural Networks

Xiyue Zhang, Benjie Wang, Marta Kwiatkowska

:30

Generating Explanations for Decisions of Classifiers using Instance Abstractions

Chunxi Ji, Adnan Darwiche

12:00

Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective

Ningsheng Zhao, Jia Yuan Yu, Krzysztof Dzieciolowski, Trang Bui

Paper 

:30

Lunch

13:00
:30
14:00

Verification of Neuro-Symbolic Agents

Elena Botoeva

Table Host 

:30

Towards Probabilistic Verification of AI Systems via Weighted Model Integration

Paolo Morettin

Table Host 

15:00

Round-table discussion

:30

Coffee break

16:00

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

:30

Concept-based Analysis of Neural Networks via Vision-Language Models

Ravi Mangal, Nina Narodytska, Divya Gopinath, Boyue Caroline Hu, Anirban Roy, Susmit Jha, Corina Păsăreanu

Paper 

17:00

Parallel Verification for δ-Equivalence of Neural Network Quantization

Pei Huang, Yuting Yang, Haoze Wu, Ieva Daukantas, Min Wu, Fuqi Jia, Clark Barrett

Paper 

:30

Verification of Neural Network Control Systems in Continuous Time

Ali ArjomandBigdeli, Andrew Mata, Stanley Bak

Paper 

Caption
Invited Talk
Presentation
VNN-COMP
Discussion
Break