Recently, the TTL team, helmed by Associate Professor Guan Zhong from the School of Microelectronics Science and Technology at Sun Yat-sen University, has made remarkable strides in the realm of 'AI for EDA'. Their research paper, 'S-Crescendo: A Nested Transformer Weaving Framework for Scalable Nonlinear System in S-Domain Representation', has been accepted for presentation at NeurIPS 2025, a premier international conference dedicated to artificial intelligence research. Previously, the team had already forged a pathbreaking innovation in the fundamental algorithms for current simulation, introducing a pioneering dynamic capacitance matching (DCM) strategy. This approach effectively circumvented the limitations inherent in traditional current response algorithms, paving the way for high-precision simulations of intricate RC load current waveforms. Moreover, the team has pioneered the integration of the Transformer architecture into the backend sign-off phase of digital circuits. Through ingenious algorithm engineering, they have facilitated RC waveform simulations for digital circuit signal lines, enhancing efficiency by several orders of magnitude while preserving accuracy on par with SPICE simulations.