Wenchao has received an NSF CAREER award to support research on specification-guided imitation learning.
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2340776
Author: Wenchao Li
Assistant Professor of ECE@BU
Trust-aware robust CBF work accepted at VehicleSec 2024
Our paper “Secure Control of Connected and Automated Vehicles Using Trust-Aware Robust Event-Triggered Control Barrier Functions” has been accepted at VehicleSec 2024. Congratulations to Sabbir who led this work!
REGLO accepted at AAAI 2024
Congratulations to Feisi, Weichao, Jiameng and our collaborators for having the paper “REGLO: Provable Neural Network Repair for Global Robustness Properties” accepted at AAAI 2024! REGLO is the first technique that enables effective repair of neural networks for global robustness properties.
POLAR-Express accepted at IEEE TCAD
Our paper “POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems” has been accepted for publication at IEEE TCAD. Congratulations to Weichao, Jiameng and our collaborators at Northwestern University, University of New Mexico, and University of Liverpool. Link to Tool: https://github.com/ChaoHuang2018/POLAR_Tool
Two papers accepted at the International Conference on Intelligent Transportation Systems (ITSC). Congratulations to Sabbir and our wonderful collaborators.
Paper on Optimal Control of Connected Automated Vehicles accepted at CCTA 2023 and won the Best Paper Award. Congratulations to Sabbir and our collaborators!
New paper on connected and autonomous vehicles (CAVs) security accepted at VehicleSec 2023. Congratulations to Sabbir who led the work!
Two papers accepted at AAMAS 2023. Congratulations to Kacper who led both works!
IARPA TrojAI Phase 2
Our team (with SRI International and Stony Brook) has been selected for Phase 2 of the TrojAI program. We will develop new technologies to defend AI systems from Trojan attacks.
New Sponsored Project by Intuit
New project sponsored by Intuit on developing a unified attribution analysis framework for interpretable deep learning.