Peter Kulits

I'm a PhD student at the Max Planck Institute for Intelligent Systems co-advised by Michael J. Black and Cordelia Schmid, and since 2026 I've been visiting Jiajun Wu at Stanford. My current research focus is on large language models and their ability to perceive and reason about the physical world.

I received my bachelor of science degree from Caltech in Dec. 2021, advised by Sara Beery and Pietro Perona, and spent the first six months of 2022 at the Mara Elephant Project in Kenya as a research fellow with Jake Wall. In September of 2022 I started my PhD.
[email] [cv] [scholar] [github]

Projects

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Ruihong Shen*, Žiga Kovačič*, Peter Kulits*, Xingrui Wang, Zizhang Li, Joshua B. Tenenbaum, Alan Yuille, Jieneng Chen, Jiajun Wu
Preprint
[project] [code] [arXiv]

BrickNet: Graph-Backed Generative Brick Assembly

Peter Kulits, Cordelia Schmid
CVPR 2026
[project] [code] [arXiv]

Generative Zoo

Tomasz Niewiadomski, Anastasios Yiannakidis, Hanz Cuevas-Velasquez, Soubhik Sanyal, Michael J. Black, Silvia Zuffi, Peter Kulits
ICCV 2025
[project] [code] [demo] [arXiv]

Reconstructing Animals and the Wild

Peter Kulits, Michael J. Black, Silvia Zuffi
CVPR 2025
[project] [code] [arXiv]

Re-Thinking Inverse Graphics With Large Language Models

Peter Kulits*, Haiwen Feng*, Weiyang Liu, Victoria Abrevaya, Michael J. Black
TMLR; ICLR 2025 Journal Track
[TMLR] [ICLR] [project] [code] [arXiv]

Text-Guided Generation and Editing of Compositional 3D Avatars

Hao Zhang*, Yao Feng*, Peter Kulits, Yandong Wen, Justus Thies, Michael J. Black
3DV 2024
[paper] [project] [code] [arXiv]

Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance

Haiwen Feng, Peter Kulits, Shichen Liu, Michael J. Black, Victoria Abrevaya
ICCV 2023
[paper] [project] [code] [arXiv]

Reconstructing Signing Avatars From Video Using Linguistic Priors

Maria-Paola Forte, Peter J. Kulits, Chun-Hao P. Huang, Vasileios Choutas, Dimitrios Tzionas, Katherine J. Kuchenbecker, Michael J. Black
CVPR 2023
[paper] [project] [code] [arXiv]

The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting

Justin Kay, Peter Kulits, Suzanne Stathatos, Siqi Deng, Erik Young, Sara Beery, Grant Van Horn, Pietro Perona
ECCV 2022
[paper] [data] [arXiv]

ElephantBook: A Semi-Automated Human-in-the-Loop System for Elephant Re-Identification

Peter Kulits, Jake Wall, Anka Bedetti, Michelle Henley, Sara Beery
ACM SIGCAS Conference on Computing and Sustainable Societies 2021
[paper] [talk] [code] [arXiv]

Generalized Unsupervised Clustering of Hyperspectral Images of Geological Targets in the Near Infrared (GyPSUM)

Angela F. Gao, Brandon Rasmussen, Peter Kulits, Eva L. Scheller, Rebecca Greenberger, Bethany L. Ehlmann
PBVS Workshop @ CVPR 2021; ICCP 2021
[paper] [talk] [poster] [arXiv]

Automated Salmonid Counting in Sonar Data

Peter Kulits, Angelina Pan, Sara Beery, Erik Young, Pietro Perona, Grant Van Horn
Tackling Climate Change with Machine Learning Workshop @ NeurIPS 2020
[paper] [talk]