Weiyin Chen

1 Introduction Clean-energy applications rely heavily on the development of robust catalysts.[1, 2] Among these, platinum (Pt)-based materials remain one of the most active and stable choices, for reactions like the hydrogen evolution reaction (HER).[3] However, the high cost of bulk Pt necessitates research into alternative catalysts[4] or strategies to utilize this precious metal more effectively.[5] Key challenges include enhancing the Pt atom efficiency,[6] improving mechanical durability...

Abstract One of the goals of ‘AI for Science’ is to discover customized materials through real-world experiments. Pioneering advances have been achieved in computational predictions and the automation of materials synthesis1–7. Yet, most materials experimentation remains constrained to using unimodal active learning (AL) approaches, relying on a single data stream. The potential of AI to interpret experimental complexity remains largely untapped8,9.

Rapid electrothermal rejuvenation of spent lithium cobalt oxide cathode Increasing use of lithium-ion batteries has triggered intensive attention to the management of end-of-life batteries. Sustainable recycling of high-value cathode materials is needed to address resource depletion and environmental challenges. Traditional battery recycling methods, including pyro- and hydro-metallurgical methods, are material-destructive processes with substantial time, energy, and chemical consumption.