Author: Wenchao Li

Assistant Professor of ECE@BU

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.

POLAR accepted at ATVA’22

Congratulations to Jiameng and our wonderful collaborators. POLAR substantially outperforms current SOTA techniques for reachability analysis of neural network-controlled systems. arXiv preprint: https://arxiv.org/abs/2106.13867

Two Papers Accepted at ICML’22

Weichao’s paper on Symbolic Reward Machine and Jiameng’s paper on Multi-View Information Bottleneck for Deep Reinforcement Learning have been accepted at ICML’22. Congrats to Weichao and Jiameng!

Paper Accepted at AAAI’22

Our paper “Programmatic Reward Design by Example” has been accepted at AAAI’22. Congrats to Weichao!