Awarded the Stanford Graduate Fellowship in April 2025
Paper 'RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination' accepted by SIGGRAPH 2025
Published 'DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation' at SIGGRAPH 2024
Co-authored 'MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model', accepted to NeurIPS 2024 (Oral Presentation)
Contributed to multiple influential works in 3D generation and rendering, including One-2-3-45++ (CVPR 2024), Zero123++ (arXiv 2023), GS³ (SIGGRAPH Asia 2024), and NRHints (SIGGRAPH 2023)
Background
PhD student in Computer Science at Stanford University
Primary research interests lie in Computer Graphics and 3D Vision
Focuses on developing Neural-native Graphics Pipelines that achieve high-quality, scalability, and generalizability
Aims to create foundational components for comprehensive world models
Earlier work centered on data-driven approaches for reconstructing and generating appearance and geometry of digital assets