• Advanced Institute of Engineering and Technology (AVITECH)

  • Seminars

    February 2, 2024: Dr. Khoa D. Doan (Vin Univeristy) Toward Reliable and Practical Machine Learning Applications

    While Machine Learning (ML) has rapidly transformed several domains and applications with incredible successes, there are also important areas where the progress is significantly slower. Specifically, there exists a widened complexity gap between the methods currently investigated in research and those used in practice in these areas. One reason is that many algorithms, despite achieving state-of-the-art performance in “controlled” research environments, usually ignore important efficiency and practical constraints of real-world problems. In this talk, I will discuss the research effort to bridge the gap between ML research and practice with examples in various ML domains. Finally, I will discuss various projects, including Trustworthy/Federated ML, Causal Inference, Low-resource NLP, and CV for Multi-modal Environmental Intelligence, and PhD/Research Assistant opportunities (co-advised by Prof. Heng Ji and others at UIUC).

    Speaker: Dr. Khoa D. Doan, Vin Univeristy

    Time: 10:00 – 10:30, Friday, February 2, 2024

    Venue: Room 212 E3, 144 Xuan Thuy, Cau Giay, Hanoi

    speaker

    Khoa D. Doan is currently an Assistant Professor of Computer Science in the College of Engineering and Computer Science, and Environment Monitoring Lab Director at the Center for Environment Intelligence at VinUniversity. Previously, he worked as an AI Researcher at Baidu Research, USA. He received his PhD in Computer Science at Virginia Tech, and MS in Computer Science at the University of Maryland, College Park. He has extensive experience working as a software engineer, data engineer/scientist, and researcher, in various industries, from scientific centers such as NASA/UMD and advertising companies such as Criteo/Baidu to ML and data analytic startups. His research focuses on developing computational frameworks that enable existing complex machine learning models to be more suitable for practical uses in various domains such as computational advertising, computer vision, natural language processing, and healthcare. Currently, his research activities include but are not limited to, deep information retrieval and its applications, generative models, and robust and reliable machine learning, with several publications at top machine learning, data mining, and computer vision conferences such as NeurIPS, ICLR, AAAI, CVPR, ICCV, SIGIR… He is a member of the Editorial Board of the new Springer’s Discover Data journal and has served as Program Committee Chair at BUGS Workshop at NeurIPS and AI for Environmental Intelligence at IEEE CAI. He is the recipient of several high-impact projects such as LLMs for healthcare, trustworthy ML, causal ML, and NLP for indigenous languages, from funding agencies such as the Gates Foundation, Grand Challenges, Amazon, and VinUni. Besides research, he spends time engaging and advising AI technology with startups.

    This seminar is jointly organized with the Department of Computer Science, the Institute for Artificial Intelligence, and the Human-Machine Interface Laboratory, VNU University of Engineering and Technology.

    SAME CATEGORY

    February 2, 2024: Prof. Heng Ji (University of Illinois at Urbana-Champaign), Combating with Misinformation and Cancer: A Unified Multimodal AI Approach to Healthy and Happy Life

    A research overview of ongoing research projects, especially focusing on two that are most related to the VinUni-UIUC Smart Health Center: (1) Misinformation Detection and Trustworthy Large Language Models; (2) Joint Natural Language and Molecule Learning for Drug Discovery. Unsurprisingly these two seemingly different research problems can be tackled with a unified approach based on […]

    January 11, 2024: Dr. Le Duc Trong (FIT-UET) Resilient Multimodal Learning for Multimodal Emotion Recognition in the Presence of Incomplete Modalities

    Multimodal Emotion Recognition in Conversation (Multimodal ERC) is a critical area of research for interpreting human communication in diverse applications. Nevertheless, the persistent issue of uncertain missing modalities poses a major hurdle, hampering the development of robust Multimodal ERC models. Existing approaches face limitations in effectively leveraging a fusion of diverse data modalities encompassing audio, […]

    January 11, 2024: Prof. Mérouane Debbah (Khalifa University of Science and Technology, UAE) TelecomGPT: The Next Big Wave in Telecomunications

    The evolution of generative artificial intelligence (GenAI) constitutes a turning point in reshaping the future of technology in different aspects. Wireless networks in particular, with the blooming of self-evolving networks, represent a rich field for exploiting GenAI and reaping several benefits that can fundamentally change the way how wireless networks are designed and operated nowadays. […]