Medha Sawhney

I am a PhD student at the Knowledge Guided Machine Learning Lab advised by Dr. Anuj Karpatne.

My research focuses on generative AI for complex scientific systems. In particular, I work primarily with diffusion models and vision-language systems, studying how generative models can learn and enforce domain-specific structures, such as physical laws or motion dynamics, from images and videos.

I’ve contributed to diverse domains through both independent and collaborative projects. My research works include:

• Diffusion models for solving PDEs in sparse, noisy, and out-of-distribution settings via physics-informed learning, with extensions to super-resolution and inpainting.
• Invertible neural networks & normalizing flows for full waveform inversion, exploring latents for reconstruction vs. manifold-learning. (GFI-ICLR’25)
• Object tracking for biomedical applications, including tiny object tracking and motion detection from noisy complex images, videos for cancer research, and inverse modeling of cellular forces.(MEMTrack-AISY’24, DLFM-PNAS’25)
• Foundation models for aquatic science, modeling lake dynamics from real-world sensor data, with a focus on pretraining strategies and handling highly sparse observational data. (LakeFM-ICMLW’25)
• Vision-language models for open-world scene graph generation (OWSGG-CVPRW’25), biological trait prediction (VLM4Bio-NeurIPS’24), and equation discovery from visual inputs.

During my PhD, I have interned as a Machine Learning Engineer Intern (MLE) at Twitter, NVIDIA and Amazon. Prior to starting my PhD, I worked as a full-time ML Engineer at HP, and hold a Bachelor’s in Electronics and Communication Engineering from Manipal Institute of Technology, Manipal, India.

Feel free to get in touch if you would like discuss, collaborate, and connect :)