Hello World.

I am Hao Tan (谭昊), I have joined Adobe Research since Aug 2021. I was a Ph.D. student at UNC CS department from 2016 to 2021, advised by Mohit Bansal. I was supported by Bloomberg Data Science Ph.D. Fellowship for my Ph.D. study. Before joining UNC, I received BS in CS from Shanghai Jiao Tong University. I was a member of ACM honored class.

Mail address: haotan@cs.unc.edu. Company email address: hatan@adobe.com

[ Github ] [ Google Scholar ]

Research

My research goal is to build a virtual world. Specifically, I want to develop the technology that can both generate a virtural world and digitalize the real world. This is the only way that I can close to XR (cross reality).

I previously worked on static 3D generation and feed-forward reconstructions. I am now working on modeling the dynamic and complex worlds. It's (maybe) obvious that the existing 3D pipeline can not support this goal in a scalable way thus I am considering rebuilding the pipeline.

I am now betting on the advance of long-context technology given the following observation:
1. Compression is intelligence. -- Ilya
2. Visual compression is spatial intelligence.
3. The definition of 3D field should not be constructive, it should be axiomatic.