Shiran Yuan

I'm a teenager who loves doing quirky stuff! Currently a Master's student at UC Berkeley. Before that I received dual B.S. degrees with Full Scholarship and Senior Award from Duke University and Duke Kunshan University.

I will be starting a PhD at Tsinghua University in Fall 2025. I've received the Best Paper Award at the International Conference on 3D Vision (3DV 2024).

Email  /  Scholar  /  Github

Research

I mainly do research on computer vision, machine learning, graphics, and applied math. Some papers are highlighted.

The first object-centric novel view synthesis model to be based on autoregressive modeling. It is several times faster than current models, exhibits significantly higher synthesis quality, scales with both model size and dataset size, and can be trained from scratch without any 2D generative base models.

Antialiasing gaussian splats using supersampling and numerical integration to reduce artifacts from changing sampling frequency.

A method combining implicit and explicit representations to achieve accurate species distribution models based on noisy presence-only data.

A framework for low-rank tensor completion that leverages both numerical priors and inter-element priors, with applications to image completion.

A single model can be slimmed at inference time to instantly achieve desired trade-offs between reconstruction quality and memory-efficiency.

Yet another Jon Barron website!