This year, we have three accepted ICCAD 2023 papers, leaded by two Ph.D. students Jincong Lu and Subed Lamichhane and Post-Doc. Dr. Liang Chen. The three papers listed below. ICCAD is one of two top conferences in the design automation (see CSrankings.com). 

The first paper [1] proposed a new machine learning based approach to estimation the full chip thermal maps of ADM multi-core CPUs using transformer deep neural networks for the first time.  The second paper [2] proposed enhanced physics-informed neural networks (PINN) based approach for full-chip thermal parametric analysis by exploring both analytic solutions and unsupervised learning method. Paper [3] developed hierarchical PINN based partial differential solving method for post-voiding stress analysis for confined interconnect metal wire trees. 

1. J. Lu, J. Zhang and S. X.-D. Tan, “Real-time thermal map estimation for AMD multi-core CPUs using transformer”,Proc. IEEE/ACM International Conf. on Computer-Aided Design (ICCAD’23), San Francisco, CA,  Nov.  2023 (accepted)
2. L. Chen, J. Lu, W. Jin and S. X.-D. Tan, “Fast full-chip parametric thermal analysis based on enhanced physics enforced neural networks”, Proc. IEEE/ACM International Conf. on Computer-Aided Design (ICCAD’23), San Francisco, CA,  Nov.  2023 (accepted)
3. S. Lamichhane, W. Jin, L. Chen, M. Kavousi, and S. X.-D. Tan, “PostPINN-EM: Fast post-voiding electromigration analysis using two-stage physics-informed neural networks”, Proc. IEEE/ACM International Conf. on Computer-Aided Design (ICCAD’23), San Francisco, CA,  Nov.  2023 (accepted)