Summary
Vaishnavi Khindkar is a Computer Vision master's student at Carnegie Mellon University and a Machine Learning Engineering Intern focused on applied video generative AI and lip-sync pipelines. With nine years of experience spanning academia and industry, she builds object-centric 4D reconstruction systems and explores diffusion/flow-based generative models, lifted representations, and reward-tilted sampling. Her research blends mathematical rigor and creative modeling—recent work includes synthetic-data diagnosis for aerial detectors and slot-based adapters over frozen geometric backbones for dynamic multi-view scenes. Previously a junior research scientist at IIIT Hyderabad, she published on pedestrian intent prediction and domain-adaptive detection, and she has practical production experience from roles at Sync Labs and Barclays. Driven by curiosity, she aims to create safer, more reliable embodied AI that generalizes from structured generative priors to real-world perception tasks.
9 years of coding experience
7 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Savitribai Phule Pune University
Master of Science - MS, Computer Vision, Master of Science - MS, Computer Vision at Carnegie Mellon University