{"ID":2856782,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15968","arxiv_id":"2510.15968","title":"Self-Attention to Operator Learning-based 3D-IC Thermal Simulation","abstract":"Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate, are too slow for iterative design. Machine learning approaches like FNO provide faster alternatives but suffer from high-frequency information loss and high-fidelity data dependency. We introduce Self-Attention U-Net Fourier Neural Operator (SAU-FNO), a novel framework combining self-attention and U-Net with FNO to capture long-range dependencies and model local high-frequency features effectively. Transfer learning is employed to fine-tune low-fidelity data, minimizing the need for extensive high-fidelity datasets and speeding up training. Experiments demonstrate that SAU-FNO achieves state-of-the-art thermal prediction accuracy and provides an 842x speedup over traditional FEM methods, making it an efficient tool for advanced 3D IC thermal simulations.","short_abstract":"Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate, are too slow for iterative design. Machine learning approaches like FNO provide faster alternatives but suffer from high-frequency information loss and high-fidelity data depend...","url_abs":"https://arxiv.org/abs/2510.15968","url_pdf":"https://arxiv.org/pdf/2510.15968v1","authors":"[\"Zhen Huang\",\"Hong Wang\",\"Wenkai Yang\",\"Muxi Tang\",\"Depeng Xie\",\"Ting-Jung Lin\",\"Yu Zhang\",\"Wei W. Xing\",\"Lei He\"]","published":"2025-10-12T13:44:42Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.AR\"]","methods":"[]","has_code":false}