I am a fourth-year PhD student at Johns Hopkins University, advised by Dr. Vishal M. Patel. My research lies at the intersection of computer vision and natural language processing, with a focus on developing advanced open-world models and multi-modal foundation models. My long-term goal is to design and deploy useful multimodal systems, enhancing their capabilities and effective deployment in diverse real-world applications.

Currently in my PhD, I have been fortunate to intern at:

1. NVIDIA (Nadine Chang, Zhiding Yu, Jose Alvarez) - Multi-modal LLM for fine-grained video grounding and hallucination estimation.
2. Qualcomm (Shubhankar, Munawar, Fatih Porikli) - Enabling SAM for Open-Vocabulary Panoptic Segmentation.
3. Salesforce (Ning Yu, Chen Xing, Mingfei Gao, Juan Carlos, Ran Xu) - Data-Efficient Open-Vocabulary Instance Segmentation.

Before joining Hopkins, during my undergraduate I interned at Mercedes-Benz Research & Development India (MBRDI) and National University of Singapore.