Hosted by: gen_c_singapore

Gen-C November 2025 Sharing


    , -

    Punggol Regional Library

    programme room (level 5)

RSVP

Details

đź”— Visual Intelligence: How Machines See and Create

Talks by Gen-C (Generative AI Learning Community) - November 2025 edition

💡 Join us for talks about Generative AI on 15 Nov 2025 (Sat)! Seats are limited so please register early to avoid disappointment! 🙂 Event details:

❗ IMPORTANT: Registration is only tracked through the below URL. Please sign up using the below URL, thank you. 👉🏻Link: https://nlb.libcal.com/event/5854983

🏠 LOCATION: Level 5 Programme Room, Punggol Regional Library, 1 Punggol Drive One, S828629

Below is the schedule,

đź§± 10.30am - 11.10am : Topic - Vision-Language Models: Bridging the Gap Between Images and Words

This presentation introduces the fascinating world of Vision-Language Models (VLMs) - AI systems that combine visual and linguistic understanding. We will cover how these models process images and text through shared representations, explore notable examples including CLIP, BLIP-2, and GPT-4V, and discuss their growing role in accessibility, education, creative design, and autonomous systems. Participants will gain a solid understanding of how VLMs work, their real-world applications, and the opportunities and challenges ahead in multimodal AI.

About the Speaker:

Sheng Jun Lim is passionate about the study of data and machine learning to improve decision making processes for financial markets. He is an engineer by training, and an efficient & effective problem solver with solid technical understanding of financial instruments and trading. As a recent graduate of BCG’s Digital Academy AI programme, he is now looking to use his skills as an Artificial Intelligence/Machine Learning Engineer to help a business fulfil its AIML needs.

11.10am - 11.30am : Q&A session

🤖 11.30am - 12.10pm : Topic - Introduction to Image and Video Generation

Ever wondered how AI can create realistic photos from just a text prompt? This talk offers a high-level introduction to the science behind image and video generation—how models learn visual patterns and connect language to pixels.

About the Speaker:

Meraldo Antonio is a Data Scientist with a strong focus on time series analysis, large language models, natural language processing, econometrics/macroeconomics, MLOps, and cloud computing (AWS & GCP). He currently works at DBS Bank, where he leverages time series analysis and LLMs to drive macroeconomic insights and analysis.

12.10pm - 12.30am : Q&A session