With advances in artificial intelligence (AI), massive computing demands have driven the development of AI chips. In particular, the recently proposed chiplet technology provides an advanced chip packaging and integration solution that offers high computing performance at a high yield rate and low cost, thus delivering solid hardware support for AI development. Chiplet-based chips are characterized by large area and high heat power, and their 3D chip stacking design leads to cooling challenges such as non-uniform heat flux distribution, long heat conduction paths for multilayer chips, and relatively thick thermal interface materials. These thermal issues are key bottlenecks limiting chip performance, making efficient chiplet thermal management a critical challenge in AI development. The progress in advanced liquid cooling technologies, including single- and two-phase liquid cooling solutions, is reviewed. Based on the cooling architecture, liquid cooling solutions can be categorized as cold-plate, near-junction-region, and immersion liquid cooling. In addition, the heat dissipation challenges and cooling strategies in 2.5D and 3D chiplets are summarized, providing a reference for the application and development of liquid cooling technologies for high-power, large-area AI chips.

Monoclinic gallium oxide (β-Ga₂O₃) is a fourth-generation semiconductor with great application potential in high-power microelectronics. Recent studies indicate that the electrical conductivity of β-Ga₂O₃ can be substantially enhanced through silicon (Si) doping. However, the effects on thermal transport, especially by considering the practical nanostructures within the crystal, have not yet been explored. To address this gap, we have developed a unified neural network potential for investigating the unexplored phonon transport of the β-(Si_xGa_1–x)₂O₃ with varying doping levels. Our atomistic simulations showed that compared to intrinsic β-Ga₂O₃, the room-temperature thermal conductivities respectively decreased by 36.5%, 33.5%, and 38.8% along the a, b, and c axes in β-SiGa₅₁₁O₇₆₈, and by 79.6%, 74.9%, and 77.8% in β-SiGa₇O₁₂. The significant degradation in phonon transport is attributed to increased lattice anharmonicity, reduced sound velocity, and most importantly, induced phonon localization due to Si substitutions. A quantitative analysis reveals that the localization primarily occurs in phonons with frequencies exceeding 2.5 THz. The vibration is confined to a region around the Si atom, extending only to its second-nearest neighbors.