The One About Agentic Solutions (ft. OCBC AI Labs)

*As the programme is still being finalized, do note that details are subject to change. More About the Sharings Kent Chiu, Yushuo Wang, Yuxuan Han (OCBC AI Labs) will share on "FORMAT‑AI: Agentic Solution for Document Intelligence at OCBC" The team will cover how FORMAT‑AI bridges long‑standing gaps in enterprise document intelligence by combining agentic architecture, Vision‑Language Models (VLMs), and Specialized Language Models (SLMs) to process complex documents and images with high accuracy and robustness. This session will provide a deep dive into the real projects, including agentic workflow orchestration and decision‑making mechanisms. The presenters will walk through how agentic reasoning is applied across document ingestion, layout understanding, visual grounding, information extraction, and validation. In addition, the team will share how Agentic Retrieval‑Augmented Generation (Agentic RAG) is designed to enable dynamic retrieval and context refinement to significantly enhance the model performance to support adaptive and reliable document intelligence use cases within OCBC. (Technical Level 200) Lee Gang (Co-Founder, Elgo AI) will share on "Designing, deploying and monitoring agentic solutions in production” Lee Gang will explore the basic foundations that allow agentic systems to be observable, controllable, and configurable. He will also explore different techniques to increase accuracy, reliability and robustness of agentic systems, and continuously monitor all these metrics in production. (Technical Level: 200) More About the Speakers Kent Chiu leads a data scientist team in OCBC Group Data Office. The team is dedicated to leveraging advanced technologies, including machine learning and agentic solutions, to drive assets in Compliance and Operations in the bank across Asia. The mission is to enhance the bank's performance by reducing costs, mitigating risks, and improving customer experiences. Kent has a decade of data science experience in top institutions across industries. His expertise spans collaborations with MIT's CSAIL (MIT Computer Science and Artificial Intelligence Laboratory) in cutting-edge research, Foxconn in 3C manufacturing, TSMC (Taiwan Semiconductor Manufacturing Company) and Lam Research in advanced semiconductor production. Yushuo Wang is a data scientist at OCBC Group’s Data Office in Singapore, with vision language models / LLMs, he has built production grade APIs which have significantly reduced the amount of manual effort required across legal, compliance, and treasury operations. Yushuo holds an MSc in Computer Control & Automation from NTU. His research covers Computer Vision and image text disentanglement, earning a top 0.5% finish in Alibaba’s Tianchi NER Challenge and 9th place in the ICCV 2019 Video Object Segmentation contest. Yuxuan Han is a Data Scientist at OCBC Group Data Office, where she works on applying machine learning and advance analytics to support business operations and compliance initiatives. Her research interest includes large language model and efficient model architecture, particularly in model compression and pruning strategy. Her work at OCBC focus on building scalable data-driven solutions and deploying machine learning models in real-world financial use cases. Lee Gang is a seasoned data scientist with more than a decade of experience. He is the founder of ELGO AI, an operating system for agentic solutions for enterprises. He previously worked in various data leadership roles across startups, MNCs and government. He holds a Master's Degree in Business Analytics from NUS and is currently also an adjunct and guest lecturer in NYP, NUS and SUSS 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