Igor Vasiljevic

I am a machine learning research scientist at the Toyota Research Institute, where I work on generative models, with a focus on efficiency and geometric grounding. I have contributed to large-scale training infrastructure and open-source efforts, our open language model training library (openlm) and pre-training of models up to 7B (including TRI-ML/mamba-7b). I also advise a number of research productization efforts. During my PhD at Toyota Technological Institute at Chicago, I worked with Greg Shakhnarovich and Matt Walter, focusing on geometric 3D vision and self-supervised learning.

Email  /  Google Scholar  /  Twitter

profile photo
Recent and selected work
(*indicates equal contribution)

Linearizing Large Language Models
Jean Mercat*, Igor Vasiljevic*, Sedrick Keh*, Kushal Arora, Achal Dave, Adrien Gaidon, Thomas Kollar
COLM, 2024

DataComp-LM: In search of the next generation of training sets for language models
DataComp-LM Team
In submission

Language models scale reliably with over-training and on downstream tasks
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Jenia Jitsev, Luca Soldaini, Alexandros G. Dimakis, Gabriel Ilharco, Pang Wei Koh, Shuran Song, Thomas Kollar, Yair Carmon, Achal Dave, Reinhard Heckel, Niklas Muennighoff, Ludwig Schmidt
In submission

Transcrib3D: 3D Referring Expression Resolution through Large Language Models
Jiading Fang, Xiangshan Tan, Shengjie Lin, Igor Vasiljevic, Vitor Guizilini, Hongyuan Mei, Rares Ambrus, Gregory Shakhnarovich, Matthew R Walter
IROS, 2024

Towards Zero-Shot Scale-Aware Monocular Depth Estimation
Vitor Guizilini, Igor Vasiljevic, Dian Chen, Rares Ambrus, Adrien Gaidon
ICCV, 2023

Depth Field Networks for Generalizable Multi-view Scene Representation
Vitor Guizilini*, Igor Vasiljevic*, Jiading Fang*, Rares Ambrus, Greg Shakhnarovich, Matthew Walter, Adrien Gaidon
ECCV, 2022

Full Surround Monodepth from Multiple Cameras
Vitor Guizilini*, Igor Vasiljevic*, Rares Ambrus, Greg Shakhnarovich, Adrien Gaidon
RA-L, 2022

Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion
Igor Vasiljevic, Vitor Guizilini, Rares Ambrus, Sudeep Pillai, Wolfram Burgard, Greg Shakhnarovich, Adrien Gaidon
3DV, 2020 (Oral Presentation)

DIODE: A Dense Indoor and Outdoor DEpth Dataset
Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter, Gregory Shakhnarovich
CVPRW, 2020












Template modified from here.