ResearchMy current work at NUS focuses on multimodal AI safety. It connects to my earlier research and industry experience in robot learning, trustworthy reasoning, and long-form video understanding at Delta, NTU, and Columbia. A recurring question is how multimodal systems remain reliable when evidence is incomplete, misleading, or adversarial. Research Interests
Multimodal AI SafetyAt NUS, I work with Prof. Hwee Tou Ng to study how multimodal AI can detect harmful video content and remain reliable when adversarial inputs attempt to manipulate its behavior. This work examines adversarial attacks, including prompt injection and attacks on systems built around multimodal language models, and investigates defenses. Real-World Robot Learning and Embodied AIMy recent industry work at Delta focused on robot-learning infrastructure, tactile and visual policy learning, VLA-style manipulation, rollout evaluation, and failure-driven improvement for real-world manipulation. My interests also include world models for embodied decision-making. A recurring question in this line of work is how embodied systems can monitor uncertainty, gather missing evidence, and recover when contact-rich execution or navigation plans start to fail. Representative work: CARe, AED, Affordance-Guided Base Placement, VLN-NF. Trustworthy LLM and MLLM ReasoningI study how language and multimodal models reason under incomplete, misleading, or physically constrained evidence, with an emphasis on false premises, underspecified affordances, abstention, and failure analysis. This direction centers on evidence-seeking behavior and constraint-aware reasoning in embodied and multimodal settings. Long-Horizon Multimodal Understanding and EvaluationAcross movies and long-form multimodal narratives, I build datasets, benchmarks, and evaluation setups for reasoning that unfolds over extended time horizons. This direction focuses on temporal coherence, narrative structure, evidence tracking, and evaluation protocols for long-context multimodal understanding. Earlier Representative WorkEarlier projects that still connect to my current research directions include the following themes. Multimodal Question Generation / QA: CaKE , GPN , SRCMSA . 3D Vision: MonoDTR , S^3 , OCID-Ref . Robotics and Embodied Grounding: GDN , SCAN , OCID-Ref . Data-Efficient Learning: SCAN , Class-agnostic Few-shot Object Counting , ReDAL . |