Best Paper Candidate

Our paper titled “ReBERT: LLM for Gate-Level to Word-Level Reverse Engineering” has been nominated for best paper in DATE’2025. Congratulations to first author Lizi Zhang and thanks to our industry collaborator Dr. Rasit Topaloglu. This paper discusses an effective way to encode a a gate-level circuit in a Hardware Description Language to enable reverse engineering to the higher bit-level using Large Language Models. We combine three embedding schemes to encode circuit information to best be understood by the BERT model. This includes a novel tree-based positional embedding scheme to encode the position of each gate within the graph structure of a circuit as a token sequence.