A KAUST-led meta-study published in Science examines the increasing ocean noise pollution from human activities like shipping and seismic blasting. The study synthesizes findings from 10,000 papers, revealing that anthropogenic noise interferes with marine animals' communication and ecological processes. The research highlights the need for policymakers to address this issue for ocean health and sustainable economies. Why it matters: Understanding and mitigating ocean noise pollution is crucial for preserving marine ecosystems and the biodiversity of the Red Sea.
Dr. Zeke Xie from HKUST(GZ) presented research on noise initialization and sampling strategies for diffusion models. The talk covered golden noise for text-to-image models, zigzag diffusion sampling, smooth initializations for video diffusion, and leveraging image diffusion for video synthesis. Xie leads the xLeaF Lab, focusing on optimization, inference, and generative AI, with previous experience at Baidu Research. Why it matters: The work addresses core challenges in improving the quality and diversity of generated content from diffusion models, a key area of advancement for AI applications in the region.
A KAUST-led study published in Science found overwhelming evidence that man-made noise negatively impacts marine fauna and their ecosystems, disrupting behavior, physiology, and reproduction. The researchers assessed over 10,000 papers to demonstrate that noise pollution from shipping, fishing, and infrastructure development harms marine life from invertebrates to whales. They call for human-induced noise to be considered a prevalent stressor at the global scale and for policy to be developed to mitigate its effects. Why it matters: This research highlights the need to consider acoustic dimensions in ocean health restoration efforts, promoting management actions to reduce noise levels and allow marine animals to re-establish their use of ocean sound.
This article discusses methods for handling label noise in deep learning, including extracting confident examples and modeling label noise. Tongliang Liu from the University of Sydney presented these approaches. The talk aimed to provide participants with a basic understanding of learning with noisy labels. Why it matters: As AI models are increasingly trained on large, noisy datasets, techniques for robust learning become crucial for reliable real-world performance.