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 embodied AI applications. I am advised by Georgia Gkioxari and Yisong Yue. Prior to grad school, I worked as a software engineer at Microsoft AI Platform. I obtained my B.S. in Computer Science and B.A. in Statistics at UChicago. I am supported by the Kortschak Scholarship.
News
| 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! |
|---|---|
| Sep 22, 2024 | Our paper “Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction” is accepted by TMLR. |
| Sep 14, 2023 | Moved to Pasadena to start my PhD at Caltech as a Kortschak Scholar! |
| Jan 05, 2023 | Microsoft filed a patent based on my work on optimizing memory footprint of the Azure pricing system! |
| Jun 02, 2021 | The fair ML sampling project I initiated got featured by PureAI: Researchers Explore Intelligent Sampling of Huge ML Datasets to Reduce Costs and Maintain Model Fairness. |
Selected Publications
-
Calibrated Uncertainty Quantification for Operator Learning via Conformal PredictionTransactions on Machine Learning Research, 2024
Latest Posts
| Nov 26, 2024 | The emerging paradigm of autoregressive VLMs |
|---|---|
| Sep 05, 2023 | Many facets of un-truth: LLM hallucination 101 |