|
Keane Ong Hi there! I'm Keane, a PhD candidate in Artificial Intelligence, co-advised by Erik Cambria (NTU), Gianmarco Mengaldo (NUS), and Paul Liang (MIT). My PhD research is co-hosted between NUS and MIT, and I'm a member of the following research groups: SenticNet, MathEXLab, and Multisensory Intelligence. My research focuses on developing socially intelligent AI, AI systems that can understand, reason about, and respond to human behaviors, intentions, and social signals in a grounded and explainable manner. I work on building the core foundations for this, including benchmarks, learning methods, and multimodal foundation models that explicitly model human affect, intent, and social dynamics. As an extension, I study the financial domain as a real-world test bed for socially intelligent AI. Financial systems are fundamentally driven by human narratives, expectations, and strategic communication, making them an ideal domain for developing and evaluating AI systems that reason about human behavior. My work in this area focuses on behavioral reasoning, narrative understanding, and modeling how human communication influences financial decision-making and outcomes. Alongside my academic research, I'm part of the founding team of FinaXai, a startup focused on advancing AI-driven financial intelligence. My broader goal is to develop socially intelligent AI systems that can deeply understand human behavior and operate effectively in complex, real-world environments. Research aside, I am a big football fan (Manchester United is my team!), and I like to ski and scuba-dive. Feel free to connect with me. |
|
News
|
Selected Publications |
 |
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
Keane Ong, Sabri Boughorbel, Luwei Xiao, Chanakya Ekbote, Wei Dai, Ao Qu, Jingyao Wu, Rui Mao, Ehsan Hoque, Erik Cambria, Gianmarco Mengaldo†, Paul Pu Liang† ArXiv preprint, 2026 preprint |
 |
Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding
Keane Ong, Wei Dai, Carol Li, Dewei Feng, Hengzhi Li, Jingyao Wu, Jiaee Cheong, Rui Mao, Gianmarco Mengaldo, Erik Cambria, Paul Pu Liang International Conference on Learning Representations (ICLR), 2026 paper / code |
 |
Deriving Strategic Market Insights with Large Language Models
Keane Ong, Rui Mao, Deeksha Varshney, Paul Pu Liang, Erik Cambria, Gianmarco Mengaldo Conference on Empirical Methods in Natural Language Processing (EMNLP), Oral, 2025 paper / code |
 |
Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization
Keane Ong, Rui Mao, Deeksha Varshney, Erik Cambria, Gianmarco Mengaldo Annual Meeting of the Association for Computational Linguistics (ACL), 2025 paper / code |
 |
Explainable Natural Language Processing for Corporate Sustainability Analysis
Keane Ong, Rui Mao, Ranjan Satapathy, Erik Cambria, Johan Sulaeman, Gianmarco Mengaldo Information Fusion, 2024 paper |