I am a research scientist at Qualcomm AI Research, leading teams developing efficient generative AI and computer vision that runs on-device — from phones and laptops to cars.

My teams work on mobile and on-device architectures for:

• Image and video generation
• Multimodal vision-language models
• Video perception and neural compression
• Generative simulators (world models) for autonomous driving

Earlier, I did a PhD on learning multimodal video representations at the University of Amsterdam.