VibePhysics: Realistic Walkthrough with Blender Animation
A demo of turning real-world capture into a navigable 3D scene — training-free 4d recon+indexing system in smooth blender navigation system. [code]
I am a Staff Research Scientist at Graphcore, focusing on world models, dynamic scenes, and novel view synthesis.
Previously I was founder and CEO of MIMI AI, a senior research scientist at Meta Reality Labs, a senior LLM research engineer at Robin AI, and an applied scientist at Amazon. Before that I worked at Scape Technologies and Academia Sinica.
I received my Ph.D. in computer science from National Taiwan University. My research focuses on world models, dynamic scenes, novel view synthesis, spatial intelligence, 3D scene understanding, and applied multimodal systems.
A demo of turning real-world capture into a navigable 3D scene — training-free 4d recon+indexing system in smooth blender navigation system. [code]
A lightweight framework for turning real-world videos and images into 3D maps, Blender scenes, and physical simulations — bridging feedforward reconstruction, sparse mapping, robotics, and physics in one CPU-friendly workflow.
MIMI AI, 2025 [code]
100k indoor data from scratch. Including layout, material, trajectories, along with 1000+ GPU-hours rendering results. Enabling pointcloud based VLM pre-training and post-training.
Project Aria, 2024 [dataset]
Tsun-Yi led cross domain teams including legal, product, and engineering along with collaboration with Anthropic and AWS team. Post-training outperforming OpenAI o1-preview in legal domain with extensive analysis. Efforts including RLHF, synthetic data, fine-tuning.
CVPR Workshops 2022 [paper]
CVPR 2022 [paper]
ECCV Workshops 2022 [paper]
arXiv 2020 [paper]
CVPR 2019 [paper]
ICCV Workshops 2019 [paper]
IJCAI 2018 [paper]
ICCV 2017 [paper]
CVPR 2016 [paper]