[2026. 05. 26] Multimodal AI for Intelligent Robotics by Prof. Ling Xiao
Title: Multimodal AI for Intelligent Robotics Abstract Recent advances in multimodal AI have significantly enhanced machines’ ability to perceive, understand, and reason about the world by integrating information from multiple modalities such as vision and language. These developments provide new opportunities for building intelligent robotic systems that can operate effectively in complex and dynamic environments. In this talk, I will present our recent research on multimodal AI, with a particular focus on vision-language models, multimodal reasoning, and efficient model design. I will discuss how multimodal representations can improve scene understanding, human intention prediction, and decision-making, while enabling efficient deployment under resource-constrained settings. As a representative application, I will introduce our recent work on social robot navigation, where multimodal perception, reinforcement learning, and multi-decision-making are jointly exploited to enable safe, efficient, and socially compliant robot behaviors in human-centered environments. Finally, I will discuss several open challenges and future directions for deploying multimodal AI in real-world robotic systems. Biography: Ling Xiao (IEEE Senior Member) is a tenured Associate Professor at Hokkaido University, Japan (2025.4 to now). She is also a Visiting Researcher at The University of Tokyo (2025.8 to now). Previously, she served as a Project Assistant Professor (2023.10-2025.3) and a Postdoctoral Researcher (2021.6-2023.9) at The University of Tokyo. She was a visiting scholar at the University of Queensland, Australia (2018.10-2019.11). Her research interests include intelligent perception and decision-making, fine-grained artificial intelligence, multimodal AI, machine learning, and robotic AI. Dr. Xiao has published 38 peer-reviewed international journal and conference papers in leading venues. Her research has received several recognitions, including the ICMR 2025 Best Paper Award, two IEICE Best Paper Awards, the 2026 NVIDIA Academic Grant Program Award, and the 2026 University of Technology Sydney (UTS) Visiting Fellowship. She currently serves as an Associate Editor of IEICE (2025.6-2029.6), a review expert for the Hong Kong Research Grants Council (RGC), and a review expert for the Japan Society for the Promotion of Science (JSPS) research funding programs. She is also actively involved in the organization of international conferences, serving as Conference Chair of APIT&CVCI 2026 and Conference Chair of IVSP&MLHMI 2027.

Robotics' End Game: Nvidia's Jim Fan
![[S5E9] 3D World Model for Robotics | Wenlong Huang | Stanford](https://i.ytimg.com/vi/0vfgm8LshmY/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLB1-6XcNflbiN3U3ERm-4s799Lbyw)
[S5E9] 3D World Model for Robotics | Wenlong Huang | Stanford

CVPR26 MedVisionFM Workshop: AI applications in oncology & cancer research | Dr Jakob Nikolas Kather

The Non-Visual Uncanny Valley in Anthropomorphic and Zoomorphic Robots

What do tech pioneers think about the AI revolution? - The Engineers, BBC World Service

AI in education showcase - Dr Yang Yang - Evidence-Informed Assessment Design: Leveraging GenAI

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

From Child Prodigy to Winning Fields Medal, Nobel of Math

Türkei – USA Highlights | Gruppe D, FIFA WM 2026 | sportstudio

Andrew Ng: Building Faster with AI

The Complete Web Development Roadmap

The Hard Fall of Porsche

Beyond the AI hype: Where we really stand and what awaits us

Conan O’Brien Mocks Trump At Harvard Commencement | Crowd Erupts During Viral Speech

How reading changes the way your brain works - BBC World Service

Abstract Black and White wave pattern| Height Map Footage| 3 hours Topographic 4k Background

ChatGPT, Gemini, Claude & Co erklärt: Wie Maschinen Sprache verstehen | Terra X Lesch & Co

Building the Impossible

