Nan Liu

I am a MSCS student at University of Illinois at Urbana-Champaign. Previously, I graduated from University of Michigan, Ann Arbor with a bachelor's degree in Computer Science in 2021.

My current research is focused on applications of generative models (i.e., energy-based models, diffusion models/score-based models). I am particularly interested in leveraging compositionality within generative models.

Email  /  Github  /  Twitter

profile photo
Publications

(* indicates equal contribution)

Compositional Visual Generation with Composable Diffusion Models
Nan Liu*, Shuang Li*, Yilun Du*, Antonio Torralba, Joshua B. Tenenbaum
ECCV 2022
[Website] [Paper] [Code] [Colab] [Demo]

Learning to Compose Visual Relations
Nan Liu*, Shuang Li*, Yilun Du*, Joshua B. Tenenbaum, Antonio Torralba
NeurIPS 2021 (Spotlight) / NeurIPS 2021 Workshop on Controllable Generative Modeling (Outstanding Paper Award)
[Website] [Paper] [Code] [MIT News]

FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
Santiago Castro, Ruoyao Wang, Pingxuan Huang, Ian Stewart,
Oana Ignat, Nan Liu, Jonathan Stroud, Rada Mihalcea
ACL 2022
[Paper] [Code]

Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models
Won Park, Nan Liu, Qi Afred Chen, Z. Morley Mao
ICIP 2021
[Paper]


Teaching

CS 543: Computer Vision (Fall 2022)

CS 441: Applied Machine Learning (Fall 2021, Spring 2022)

I use this webpage template from here