PANEL & COMPETITION

Young Woman Rising Star in AI

Chair: Prof. Min-Chun Hu

Professor, the Department of Computer Science at National Tsing Hua University, Taiwan

Learning Representations for Robust Human-Robot Interaction

Dr. Yen-Ling Kuo 郭彥伶博士
Assistant Professor, the computer science at the University of Virginia, USA

Abstract

For robots to robustly and flexibly interact with humans, they need to acquire skills to use across scenarios. One way to enable the generalization of skills is to learn representations that are useful for downstream tasks. Learning a representation for interactions requires an understanding of what (e.g., objects) as well as how (e.g., actions, controls, and manners) to interact with. Failure to generalize in different scenarios could cause robots to develop confusing or harmful behaviors in a variety of human-centric applications ranging from elderly care to driving.
In this talk, I will present my work on leveraging the compositional nature of language and reward functions to learn representations that generalize to novel scenarios. I will show that together with the information from multiple modalities, the learned representation can reason about task progress, future behaviors, and the goals/beliefs of an agent. I will demonstrate how these ideas can be used for language understanding and social interactions. I will conclude with research directions on endowing robots with generalizable reasoning skills and long-term human-AI interactions.

Biography

Yen-Ling Kuo is an Anita Jones Faculty Fellow and Assistant Professor in Computer Science at the University of Virginia. Her research interests lie at the intersection of artificial intelligence and cognitive science. She develops machine learning models that provide robots with generalizable reasoning skills including language understanding, social interactions, and commonsense reasoning. Yen-Ling received her Ph.D. in Computer Science from MIT and BS/MS degrees in Computer Science and Information Engineering from National Taiwan University. She is a recipient of the CBMM-Siemens Graduate Fellowship.

從人工智慧到人類智慧,還有多遠?

Dr. Hsiao-Yu Tung 童筱妤博士
Google DeepMind, US

Abstract

近年來人工智慧正以爆炸性的速度在成長,Chat-GPT和許多大模型的誕生讓許多各行各業的人都能更直接的感受人工智慧能為我們帶來的便利性和衝擊性。這些模型似乎能回答一些一般人可能也覺得很困難的問題,像是作詩或是解釋哲學問題,但與此同時,你可能也會發現這些模型好像很常會“睜眼說瞎話”,或在極其簡單的問題上犯錯。究竟這些新型的人工智慧和人類智慧還相距多遠?我們有哪些方法能夠讓人工智慧更接近人類智慧?我將在此次演講跟大家分享我在這些問題上的想法和研究成果,也希望能以此激勵更多關於這些問題的討論。

Biography

大學畢業於台灣大學電機工程學系,在此期間首次認識到機器學習便為此著迷。爾後前往美國卡內基梅隆深造,順利取得機器學習的碩士及博士學位,研究題目為利用自監督學習建立機器基本常識(machine common sense)。畢業以後,加入了MIT prof. Josh Tenenbaum 的團隊,嘗試理解機器學習及認知科學的連結,目前在Google DeepMind擔任研究工程師。

Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

Dr. An-Zi Yen 顏安孜博士
Assistant Professor, the Department of Computer Science at National Yang Ming Chiao Tung University, Taiwan

Abstract

Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.

Biography

Dr. An-Zi Yen is an Assistant Professor in the Department of Computer Science at National Yang Ming Chiao Tung University. Her research interests include natural language processing and information retrieval. Her work has been published in AAAI, EMNLP, WWW, SIGIR, and so on. Dr. Yen's awards and honors include the Honorable Mention of Doctoral Dissertation Award of ACLCLP in 2020 and the distinguished PC member in IJCAI 2023. She served as the web chair of SIGIR 2023, and as PC members of representative conferences including AAAI, IJCAI, CIKM, and EACL.

AI智能選股真的可行嗎?
Recent Advancement in Portfolio Optimization based on Novel Assessment Strategies and Quantum-inspired Search Algorithms

Dr. Shu-Yu Kuo 郭姝妤博士
Postdoctoral Research Fellow, Department of Physics and Center for Quantum Science and Engineering, National Taiwan University, Taiwan

Abstract

Recent Advancement in Portfolio Optimization based on Novel Assessment Strategies and Quantum-inspired Search Algorithms.
The task of optimizing the portfolio is to have a stable return and lower its overall risk. Selecting the best combination of stocks with low risk and high return simultaneously is a significant challenge for investors. Deciding which stocks should be invested in or not and finding the optimal combination of parameters for different technical indicators with targets and different investment situations are quite difficult in such a large solution space as well. In this talk, I will talk about our recent works on portfolio optimization based on novel assessment strategies. Experiments show many interesting and promising results by using quantum-inspired search algorithms.

Biography

Shu-Yu Kuo received the Ph.D. degree from the Department of Computer Science and Information Engineering, National Chi Nan University, Nantou, Taiwan, in 2018. She was a Visiting Postdoctoral Research Associate with the Department of Electrical Engineering at Princeton University, Princeton, NJ, and at the University of Washington, Seattle, WA, USA, in 2018 and 2019. She is currently with the Department of Physics and Center for Quantum Science and Engineering, National Taiwan University, Taipei, Taiwan. Her research interests include metaheuristic algorithms, quantum-inspired algorithms, quantum secure communication and computation, network security, and financial technology.

Scroll to Top