Hi! I'm a senior Research Engineer at NVIDIA, part of the Spatial Intelligence Lab. My current work focuses on exploring the use of multimodal large language models (MLLMs) to understand data value, guide data selection, and mitigate hallucinations. Previously, I worked on model-centric efficiency techniques such as pruning, distillation, and quantization. Prior to joining NVIDIA, I graduated with a Masters from Carnegie Mellon University majoring in computer vision (MSCV).
Explore my research and stay updated by following my work on my Google Scholar page!