Biography

I am a Research Scientist at Google Research. My long-term research goal is to architect Native Omni Models as the cognitive engine for ASI. I focus on building multimodal foundation models to create unified generalist agents capable of mastering complex digital and physical environments.

I am currently exploring the intersection of World Models, Efficient AI, and System 2 Reasoning, specifically:

• Architecting asynchronous and streaming multimodal frameworks that integrate real-time generation and reasoning.
• Scaling unified transformers on internet-scale multimodal data to construct high-fidelity and interactive world models.
• Bridging multimodal generative models with causal physics priors to enable robust generalization and long-horizon decision-making.

I am open to discuss the future of Multimodal LLMs, Multimodal Generative AI, World Models, and Agentic Foundation Models. I welcome collaborations across industry and academia. Authorized to work in US and Australia.

To accelerate the advent of machine intelligence and sustainable future