Abstract Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However, most language tasks are partially or fully cooperative, so it is an[…]
Abstract High-quality user feedback is essential for effective human-AI interaction. It bridges knowledge gaps, corrects drift, and shapes system behavior; both during the interaction and throughout model development. However, despite its importance, in-the-wild human-AI conversations[…]
Abstract Unstructured data is pervasive in our daily lives, appearing in forms such as meeting and interview transcripts, written notes, and social media posts. These data often contain valuable human knowledge and insights. To uncover[…]
Abstract I had a great time living in a 14th century monastery, hanging out with Emma and Augi, pretending to be a doctor or a patient, and learning to produce speech in Sarawak Malay, Central[…]
Abstract Current AI systems fail when encountering unfamiliar situations. This talk presents a unified approach where synthesis models help analysis models handle new scenarios by transforming unfamiliar inputs into recognizable forms. We demonstrate a generative[…]
Abstract Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with many choices,[…]
Abstract As LLMs become increasingly integrated into academic workflows, their influence is both promising and precarious. In this talk, we will explore three facets of this evolving intersection. – The Good: LLMs executing aspects of peer[…]
