Matt Y. Cheung
I am a PhD student in Electrical and Computer Engineering at Rice University advised by Ashok Veeraraghavan and Guha Balakrishnan. I work on uncertainty quantification, specifically Conformal Prediction for medical imaging problems, as well as generative models and hallucinations. I am also a trainee in the NIH NLM Training Program in Biomedical Informatics and Data Science. I received my M.S. in Electrical and Computer Engineering from Rice University in 2023 and my B.S. in Electrical Engineering (cum laude) from UC Davis in 2020.
news
| May 29, 2026 | New paper on arXiv Conformal Certification of Reasoning Trace Prefixes. |
|---|---|
| Mar 02, 2026 | New paper on arXiv Efficient Conformal Volumetry for Template-Based Segmentation. |
| Jan 26, 2026 | Our paper COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics was accepted at ICLR 2026. |
| Jan 13, 2026 | Our paper Bias-Aware Conformal Prediction for Metric-Based Imaging Pipelines was accepted at IEEE ISBI 2026 as an Oral. |
| Jul 21, 2025 | Our paper Metric-guided Conformal Bounds for Probabilistic Image Reconstruction was accepted at UNSURE @ MICCAI as a Long Oral Presentation. |
latest posts
| Mar 28, 2026 | Learn-then-Test |
|---|---|
| Mar 28, 2026 | Survey of Conformal Predictions for LLMs |
| Mar 23, 2026 | Split Conformal Prediction and Non-Exchangeable Data |
| Mar 12, 2026 | Transformers 1-100: From Seminal Papers to Modern Standard Practice |
| Mar 12, 2026 | Transformers 0: A Simple Mental Model |
selected publications
-
COMPASS: Robust Feature Conformal Prediction for Medical Segmentation MetricsICLR, 2026 -
Metric-Guided Conformal Bounds for Probabilistic Image ReconstructionUNSURE Workshop at MICCAI (Long Oral), 2025 -
Wearable blood pressure monitoring devices: Understanding heterogeneity in design and evaluationIEEE Transactions on Biomedical Engineering, 2024