|
Nhi Pham I'm a PhD student at the Max Planck Institute for Informatics in Saarbrücken, Germany, where I am advised by Prof. Bernt Schiele and Dr. Jonas Fischer. As part of PhD preparatory phase, I was jointly supervised by Dr. Adam Kortylewski on interpreting image classifiers with 3D neural object volumes. Before this, I received my B.S in Computer Science and Mathematics at New York University, where I worked on computational linguistics with Prof. Adam Meyers, and on operator theory with Prof. Ilya Spitkovsky. I also interned at Goldman Sachs, Amazon AWS AI, and Meta (Facebook). Email / CV / Google Scholar / Twitter / Github |
|
News01.2026 Our paper CAVE is accepted at ICLR 2026! 04.2025 I presented CAVE at the Generative Intelligence Lab! 03.2025 I’ve finished my PhD preparatory phase in the IMPRS-TRUST program, and officially joined D2 MPII for my PhD! 12.2024 H-POPE is accepted to NeurIPS 2024 - Statistical Foundations of LLMs and Foundation Models Workshop! |
ResearchMy current research interest lies in geometric representation learning, with an emphasis on interpretable and robust vision models grounded in 3D structure. I am also interested in extending these ideas to video diffusion models, where learning holistic, geometry-aware tokens can support structured reconstruction and generation over time. In my previous life, I enjoyed playing around with special matrices and operator theory. |
|
Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
(CAVE)
Nhi Pham, Artur Jesslen, Bernt Schiele, Adam Kortylewski*, Jonas Fischer* (*equal senior advisorship) Accepted to ICLR, 2026 paper / arXiv / project page / code Design an inherently-interpretable and robust classifier by extending existing 3D-aware classifiers with concepts extracted from their volumetric representations for classification. We also propose a new metric to measure 3D consistency of concepts. |
|
H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in
Large Vision-Language Models
Nhi Pham*, Michael Schott* NeurIPS - Statistical Foundations of LLMs and Foundation Models Workshop, 2024 arXiv A coarse-to-fine-grained benchmark that systematically assesses hallucination in object existence and attributes. |
|
On 3-by-3 Row Stochastic Matrices
Nhi Pham, Ilya Spitkovsky Special Matrices, 2023 paper The known constructive tests for the shapes of the numerical ranges in the 3-by-3 case are further specified when the matrices in question are row stochastic. Auxiliary results on the unitary (ir)reducibility of such matrices are also obtained. |
Others |
Academic Service |
Reviewer: T-PAMI 2026, XAI4CV 2025, XAI4CV 2024 |
Graduate Teaching |
Teaching Assistant, Explainable
Machine Learning (ExML) Seminar, Winter 2025/26
Teaching Assistant, High-level Computer Vision, Summer 2025 Teaching Assistant, Neural Networks: Theory and Implementation, Winter 2024/25 |
|
Source code and design are borrowed from Jon Barron's website. |