Ziqi Ma
Computer Vision @ California Institute of Technology.
Hello! I am Ziqi, a PhD student at Caltech. I work on 3D computer vision, with the ultimate goal of enabling AI in the physical world. I am advised by Georgia Gkioxari and Yisong Yue. I recently interned at Meta SuperIntelligence Labs with Sasha Sax. Prior to grad school, I was at Microsoft and The University of Chicago. I am supported by the Kortschak Scholarship.
News
| Dec 17, 2025 | Steer3D is released! Generative 3D models can now listen to your commands - simply edit and customize the generations with natural language! |
|---|---|
| Nov 19, 2025 | SAM 3D is released! Now you can upload an image, click on a few objects, and get an interactive 3D world! |
| Jul 27, 2025 | “Find Any Part in 3D” is accepted into ICCV 2025 and as a Highlight✨! See you all in Hawaii! |
| Jun 23, 2025 | Started my internship at Meta FAIR Perception team! |
| Nov 20, 2024 | Check out our new work “Find Any Part in 3D”: a model that can localize any part of any object based on any text query! |
Selected Publications
-
Calibrated Uncertainty Quantification for Operator Learning via Conformal PredictionTransactions on Machine Learning Research, 2024
Latest Posts
| Aug 06, 2025 | Find3D: Localizing Semantic Concepts in the 3D Space |
|---|---|
| Jul 05, 2025 | 3D & The Bitter Lesson – CVPR25 Rambling Thoughts |
