Now showing items 22-24 of 52965

    • Pico-Scale Science for Pedestrian-Scale Solutions (PSS4PSS): A Computational Toolbox Leveraging Molecular Simulation for Pedestrian Dynamics 

      Chen, Samuel; Collins, Emerson; Cheng, Vincent; Kramer, Kelby; Wang, Gerald (ACM|The 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2024-10-29)
      Efficient and accurate simulations of pedestrian dynamics are critical for the smart cities of the future. In this work, we present a computational toolbox that accelerates such simulations relative to a popularly used ...
    • Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization 

      Majumder, Navonil; Hung, Chia-Yu; Ghosal, Deepanway; Hsu, Wei-Ning; Mihalcea, Rada; e.a. (ACM|Proceedings of the 32nd ACM International Conference on Multimedia, 2024-10-28)
      Generative multimodal content is increasingly prevalent in much of the content creation arena, as it has the potential to allow artists and media personnel to create pre-production mockups by quickly bringing their ideas ...
    • FSL-QuickBoost: Minimal-Cost Ensemble for Few-Shot Learning 

      Bai, Yunwei; Cai, Bill Yang; Tan, Ying Kiat; Zheng, Zangwei; Chen, Shiming; e.a. (ACM|Proceedings of the 32nd ACM International Conference on Multimedia, 2024-10-28)
      Few-shot learning (FSL) usually trains models on data from one set of classes, but tests them on data from a different set of classes, providing a few labeled support samples of the unseen classes as a reference for the ...