Artificial Intelligence (AI) has long aspired to mimic the unique human capacity for understanding and creating novel combinations from known elements. This quest takes a significant step forward with CDS Assistant Professor of Psychology and Data Science Brenden Lake and ICREA research professor Marco Baroni’s pioneering research, which introduces Meta-Learning…

The quest to refine AI’s understanding of extensive textual data has recently been advanced due to two recent papers by CDS PhD student Jason Phang, who is the first author of two recent NLP papers that were presented at ICML 2023 and EMNLP 2023. Phang’s first paper, “HyperTuning: Toward Adapting…

The ability to precisely identify the location of a sound using audio alone is a skill humans have honed over millions of years. At the recent DCASE 2023 conference, Chris Ick, a PhD candidate at CDS, presented innovative research that advances the state of the art of the artificial implementation…

We’re excited to announce that many CDS faculty, researchers, and students will present at the upcoming thirty-seventh 2023 NeurIPS (Neural Information Processing Systems) Conference, taking place Sunday, December 10 through Saturday, December 16. The conference began in 1987 and focuses on the advancement of research in AI and machine learning…

Yann LeCun is a renowned deep learning pioneer and one of the most important minds in AI, and over the past few years he has been developing a comprehensive theory of machine learning, centered around “energy-based models,” which he calls “the only way to formalize and understand all model types.”…

Self-supervised learning (SSL) has emerged as a powerful technique for training deep neural networks without extensive labeled data. However, unlike supervised learning, where labels help identify relevant information, the optimal SSL representation heavily depends on assumptions made about the input data and desired downstream task. This is the subject of…

Multimodal learning, a technique that trains machine learning models using multiple data modalities simultaneously, such as images and text, stands out as a promising avenue. However, a recurring challenge has been observed: multimodal models often fail to utilize all data modalities effectively. Taro Makino, a fourth-year CDS PhD student, along…

Artificial Intelligence (AI) has been a hot topic particularly since the rise of ChatGPT this year. This marked the first time we could engage in conversation with a machine as we would with other humans, however flawed. This occurrence has created a new “paradigm shift” in the field of AI…

The advent of large language models (LLMs) based on transformer architecture, which drives products like ChatGPT, has revolutionized machine learning. However, transformers’ propensity to ‘hallucinate’ — producing coherent yet incorrect answers — remains an impediment to being able to trust this kind of technology enough to use it in critical…