Efficient Generative Models
ML Researcher · Generative Models & Computer Vision
Researching adaptive multimodal systems that use computation more intelligently.
I recently completed AI Residency at Google DeepMind, where I worked on efficient generative models across Veo and Gemini.
Google DeepMindAI Residency · 2024–2026
ICML · ECCV · WACV
ICLR-W · CVPR-W · ICCV-W · ACM MM-W
ACM MM Asia (Best Demo Paper)
2 US PatentsEfficient visual generation
Selected research
All publications →
Recent work in efficient visual generation.
Elastic Looped Transformers for Visual Generation
Adaptive looped architectures that make visual generation more computationally elastic.
Read paper ↗
Masked Generative Nested Transformers
Nested generative transformers designed to benefit from additional computation at decode time.
Read paper ↗
Design-o-meter
A framework for evaluating and iteratively refining the aesthetic quality of graphic designs.
View project ↗