I am a final-year PhD student in Computer Science at the University of Toronto, co-advised by Alec Jacobson and Andrea Tagliasacchi. My research focuses on 3D computer vision and graphics, with an emphasis on robust 3D/4D reconstruction, uncertainty estimation, and camera pose estimation. More recently, I have been exploring reinforcement learning methods for embodied agents in 3D worlds.

I have interned at Waabi AI, Google DeepMind, and Wayve, and spent time as a visiting student with Angjoo Kanazawa's lab at UC Berkeley. Broadly, I am interested in robust and uncertainty-aware 3D perception, and how it can support learning and decision-making in the real world.

Before my PhD, I completed my B.Sc. at Sharif University of Technology, where I also had research internships at TU Munich and UBC.

I am on the 2026 job market and seeking industry research positions in 3D vision, graphics, and robotics.


Selected Publications

Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration

Lily Goli, Justin Kerr, Daniele Reda, Alec Jacobson, Andrea Tagliasacchi, Angjoo Kanazawa

arXiv 2026

RoMo: Robust Motion Segmentation Improves Structure from Motion

Lily Goli*, Sara Sabour*, Mark Matthews, Marcus Brubaker, Dmitry Lagun, Alec Jacobson, David J. Fleet, Saurabh Saxena, Andrea Tagliasacchi

* Equal contribution   Equal advising

ICCV 2025

SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting

Lily Goli*, Sara Sabour*, George Kopanas, Mark Matthews, Dmitry Lagun, Leonidas Guibas, Alec Jacobson, David J. Fleet, Andrea Tagliasacchi

* Equal contribution

Transactions on Graphics (TOG) 2025

3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction

Maria Taktasheva, Lily Goli, Alessandro Fiorini, Zhen (Colin) Li, Daniel Rebain, Andrea Tagliasacchi

Equal advising

NeurIPS 2025

Bayes’ Rays: Uncertainty Quantification for Neural Radiance Fields

Lily Goli, Cody Reading, Silvia Sellán, Alec Jacobson, Andrea Tagliasacchi

CVPR 2024 (Highlight)

BANF: Band-limited Neural Fields for Levels of Detail Reconstruction

Ahan Shabanov, Shrisudhan Govindarajan, Cody Reading, Lily Goli, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi

CVPR 2024

nerf2nerf: Pairwise Registration of Neural Radiance Fields

Lily Goli, Daniel Rebain, Sara Sabour, Animesh Garg, Andrea Tagliasacchi

ICRA 2023, CVPR workshop (XRNeRF) 2023, Computer Vision News cover (March 2023)

Longitudinal Quantitative Assessment of COVID-19 Infection Pro- gression from Chest CTs

Lily Goli*, Seong Tae Kim*, Magdalini Paschali, Ashkan Khakzar, Matthias Keicher, Tobias Czempiel, Egon Burian, Rickmer Braren, Nassir Navab, Thomas Wendler

* Equal contribution

MICCAI 2021

For a full list of publications, please refer to my Google Scholar page.