What does it take for AI-powered robots to work in the real world?
From robots that can reason across different tasks, to models that translate what they see and understand into actions, AI is expanding what robots can do beyond controlled environments.
But building robots that can operate reliably in the real world requires more than better models. They need to reason and plan, remember what has happened, respond to changes around them, and act reliably despite constraints such as latency, connectivity, and uncertainty.
Together with IMDA, we are bringing you an AI Wednesdays × Technical Sharing Session edition focused on AI and robotics, exploring the models, systems, and infrastructure shaping how intelligent robots are built and deployed beyond the lab.
More About the Sharings
Soujanya Poria (Associate Professor, NTU) will share on “Beyond Better Actions: What Generalist Physical Agents Still Need.”
What will it take to build robots that can perform many different tasks across different environments?Soujanya will argue that the challenge isn't simply collecting more robot data. Large language and multimodal models can already reason and plan, but physical agents must coordinate that slower reasoning with fast control, remember what happened earlier, and know when they need more evidence before acting.He'll explore this through three pieces of work: GE-Act 2.0, a world action model pretrained at scale; MemBodied, which adds persistent memory to vision-language-action models; and RoboQuest, a long-horizon benchmark that separates failures in evidence gathering, interpretation, planning, execution, and verification.Together, these point towards a different challenge for generalist physical agents: coordinating fast control, persistent memory, and higher-level planners that know when to gather more evidence, replan, and check their own work.
Raphael Yee (Director, Griffin Labs) will share on “Griffin Alpha.”
Raphael will share how Griffin Labs built Griffin Alpha, an open-weight vision-language-action (VLA) model developed in Singapore, and why the team chose to open-source it.He'll unpack how the model was developed and share results from Alpha-S, which matches π0.5 on LIBERO and ranks first among VLA models on RoboTwin 2.0 under changes in lighting, clutter, and backgrounds.
Ernest Tan (Assistant Professor, Infocomm Technology Cluster, SIT) will share on “From Research to Reality: Edge Intelligence for AI-Enabled Robotics.”
When autonomous robots operate at scale, relying entirely on the cloud can introduce challenges around latency, connectivity, and reliability. Ernest will explore how edge intelligence, 5G/6G communications, and distributed AI can help make robotic systems more responsive and reliable.He'll share ongoing research and testbed developments in multi-link connectivity, inference-aware offloading, cache-driven inference, and semantic-aware task offloading, alongside their practical implications for robotics in facilities management, public safety, and the built environment.
More About the Speakers
Soujanya Poria is an Associate Professor in the School of Electrical and Electronic Engineering (EEE) at Nanyang Technological University (NTU). His research interests include trustworthy AI, AI safety, multimodal AI, and embodied AI.
Raphael Yee is Director of Griffin Labs, LionsBot’s embodied AI subsidiary. His team develops frontier embodied AI capabilities, including Griffin-Alpha, a state-of-the-art VLA model competitive on leading benchmarks. He holds a BEng in Computer Science from the Singapore University of Technology & Design.
Dr Ernest Tan currently serves in the Infocomm Technology Cluster at the Singapore Institute of Technology (SIT) and is Deputy Programme Leader for the Applied Artificial Intelligence (AAI) programme. His research interests are in edge intelligence for real-time artificial intelligence (AI) services in Internet of Things (IoT) networks. Specifically, his research focuses on edge caching and computation offloading for real-time AI services, with the aim of overcoming the computation and battery constraints of IoT devices and embodied agents.He graduated with First Class Honours in Computer Engineering from Nanyang Technological University (NTU) in 2015 and earned his Ph.D. in Computer Engineering from NTU in 2020. His doctoral research was supported by the Economic Development Board’s Industrial Postgraduate Programme (IPP) in collaboration with Airbus Singapore, where he also served as a Research Engineer from 2016 to 2020.
Community Partner: IMDA’s Technical Sharing Sessions
IMDA’s Technical Sharing Sessions (TSS) is a monthly forum for practitioners in Singapore’s emerging technology community to tech-spar on AI, Digital Trust and Safety, 5G, Quantum Technologies, and Green Software.
To date, TSS has featured over 85 speakers across 10 countries, including leaders from Google DeepMind, IBM, Cohere, SAP, Samsung, and Microsoft Research.
Join their mailing list to be informed of future sessions! Stay Connected With Us!
More About The Series
AI Wednesdays is Lorong AI’s weekly gathering, bringing together practitioners, researchers and innovators for technical discussions on research insights, product development and engineering practices.
Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X
