Igor Gilitschenski
@igilitschenski.bsky.social
Assistant Professor in Computer Science at UofT.
I'm looking for graduate students to join my group in fall 2026. We work at the intersection of Computer Vision, Deep Learning, and Robotics.
The goal of our work is to create and understand organic 🍀 simulation systems, i.e., controllable data-curation engines built from real-world data. 1/n
The goal of our work is to create and understand organic 🍀 simulation systems, i.e., controllable data-curation engines built from real-world data. 1/n
November 22, 2025 at 8:50 PM
I'm looking for graduate students to join my group in fall 2026. We work at the intersection of Computer Vision, Deep Learning, and Robotics.
The goal of our work is to create and understand organic 🍀 simulation systems, i.e., controllable data-curation engines built from real-world data. 1/n
The goal of our work is to create and understand organic 🍀 simulation systems, i.e., controllable data-curation engines built from real-world data. 1/n
Together with our brilliant graduate researcher Ziyi Wu and our fantastic undergrad, Brayden Zhang, we had a wonderful time at #ICCV2025!
October 25, 2025 at 2:32 AM
Together with our brilliant graduate researcher Ziyi Wu and our fantastic undergrad, Brayden Zhang, we had a wonderful time at #ICCV2025!
Interesting @anthropic.com work on LLM poisoning. I'd argue that the glass is half full, and this can be interpreted as a positive result: Regardless of model size, the same number of samples seems to be sufficient to learn a new "skill". www.anthropic.com/research/sma...
A small number of samples can poison LLMs of any size
Anthropic research on data-poisoning attacks in large language models
www.anthropic.com
October 10, 2025 at 3:06 AM
Interesting @anthropic.com work on LLM poisoning. I'd argue that the glass is half full, and this can be interpreted as a positive result: Regardless of model size, the same number of samples seems to be sufficient to learn a new "skill". www.anthropic.com/research/sma...
Excited to have been appointed as a faculty member at @vectorinstitute.ai. 🎉 This would not have been possible without the amazing work of my collaborators and the brilliant students in my group within @uoftcompsci.bsky.social. We all look forward to deepening ties with the Vector community. ❤️
October 1, 2025 at 10:23 PM
Excited to have been appointed as a faculty member at @vectorinstitute.ai. 🎉 This would not have been possible without the amazing work of my collaborators and the brilliant students in my group within @uoftcompsci.bsky.social. We all look forward to deepening ties with the Vector community. ❤️
Want to help train the next generation of leaders, researchers, and innovators in CS? We are looking for teaching stream faculty to join us at @uoftcompsci.bsky.social. Check out our job posting and join a team of brilliant colleagues and amazing students. 🇨🇦❤️💻 academicjobsonline.org/ajo/jobs/30410
University of Toronto, Department of Computer Science
Job #AJO30410, Assistant Professor, Teaching Stream - Computer Science, Department of Computer Science, University of Toronto, Toronto, Ontario, CA
academicjobsonline.org
October 1, 2025 at 12:19 AM
Want to help train the next generation of leaders, researchers, and innovators in CS? We are looking for teaching stream faculty to join us at @uoftcompsci.bsky.social. Check out our job posting and join a team of brilliant colleagues and amazing students. 🇨🇦❤️💻 academicjobsonline.org/ajo/jobs/30410
Proud German advisor moment: Discovered a pair of Birkenstocks under a grad student's desk.
September 4, 2025 at 2:32 PM
Proud German advisor moment: Discovered a pair of Birkenstocks under a grad student's desk.
Reposted by Igor Gilitschenski
Would you be surprised to learn that many empirical implementations of value-aware model learning (VAML) algos, including MuZero, lead to incorrect model & value functions when training stochastic models 🤕? In our new @icmlconf.bsky.social 2025 paper, we show why this happens and how to fix it 🦾!
June 19, 2025 at 2:40 AM
Would you be surprised to learn that many empirical implementations of value-aware model learning (VAML) algos, including MuZero, lead to incorrect model & value functions when training stochastic models 🤕? In our new @icmlconf.bsky.social 2025 paper, we show why this happens and how to fix it 🦾!
Thrilled to share the work that our lab will present at
@cvprconference.bsky.social. Check out the papers and meet @kai-he.bsky.social, @yashkant.bsky.social, @dazitu616.bsky.social, and Toshiya Yura in Nashville at their poster sessions!
@cvprconference.bsky.social. Check out the papers and meet @kai-he.bsky.social, @yashkant.bsky.social, @dazitu616.bsky.social, and Toshiya Yura in Nashville at their poster sessions!
June 10, 2025 at 8:04 PM
Thrilled to share the work that our lab will present at
@cvprconference.bsky.social. Check out the papers and meet @kai-he.bsky.social, @yashkant.bsky.social, @dazitu616.bsky.social, and Toshiya Yura in Nashville at their poster sessions!
@cvprconference.bsky.social. Check out the papers and meet @kai-he.bsky.social, @yashkant.bsky.social, @dazitu616.bsky.social, and Toshiya Yura in Nashville at their poster sessions!
Ai4Science is doing a great job at applying AI to accurately model physics for one (or a few) phenomena at a time. Video models sacrifice such accuracy in favour of huge diversity. The big challenge for robot learning researchers is to strike a balance between these two.
June 2, 2025 at 10:27 PM
Ai4Science is doing a great job at applying AI to accurately model physics for one (or a few) phenomena at a time. Video models sacrifice such accuracy in favour of huge diversity. The big challenge for robot learning researchers is to strike a balance between these two.
In Germany, there is a tradition of creating funny hats for doctoral graduates. 🎓 @cvoelcker.bsky.social brought this tradition to my group and, together with Umangi Jain, spearheaded the construction of a masterpiece for our first PhD graduate, @ashmrz.bsky.social. 1/2
May 28, 2025 at 5:40 PM
In Germany, there is a tradition of creating funny hats for doctoral graduates. 🎓 @cvoelcker.bsky.social brought this tradition to my group and, together with Umangi Jain, spearheaded the construction of a masterpiece for our first PhD graduate, @ashmrz.bsky.social. 1/2
Compared to huge budget cuts, barring Harvard from enrolling any international students may seem unimportant. The opposite is true. Graduate students are the primary generators of research. Staying world-class requires the world's brightest minds.
www.cnn.com/2025/05/22/u...
www.cnn.com/2025/05/22/u...
www.cnn.com
May 22, 2025 at 7:38 PM
Compared to huge budget cuts, barring Harvard from enrolling any international students may seem unimportant. The opposite is true. Graduate students are the primary generators of research. Staying world-class requires the world's brightest minds.
www.cnn.com/2025/05/22/u...
www.cnn.com/2025/05/22/u...
Today is one of the most exciting days of my academic career: my first PhD student graduated. 🎉 Huge congrats, @ashmrz.bsky.social! 🥂 I am grateful for the opportunity to have worked with you and could not have wished for a better start. 🚀 1/4
May 12, 2025 at 4:41 PM
Today is one of the most exciting days of my academic career: my first PhD student graduated. 🎉 Huge congrats, @ashmrz.bsky.social! 🥂 I am grateful for the opportunity to have worked with you and could not have wished for a better start. 🚀 1/4
Great meeting @sramamoorthy.bsky.social and David Richardson from @edinburgh-uni.bsky.social
May 9, 2025 at 4:26 PM
Great meeting @sramamoorthy.bsky.social and David Richardson from @edinburgh-uni.bsky.social
Congrats on your election victory, @liberalca.bsky.social and @mark-carney.bsky.social! If I had one wish for Canada's new government, it would be this: stop delaying visas and make it easier for the world's top scientists, including research-focused graduate students, to come to Canada. 🍁
April 30, 2025 at 7:20 PM
Congrats on your election victory, @liberalca.bsky.social and @mark-carney.bsky.social! If I had one wish for Canada's new government, it would be this: stop delaying visas and make it easier for the world's top scientists, including research-focused graduate students, to come to Canada. 🍁
Perfect time to catch up on some missed-out reading.
April 30, 2025 at 11:10 AM
Perfect time to catch up on some missed-out reading.
A rare sighting of @csprofkgd.bsky.social, showing his students some cool @vscode.dev productivity hacks.
April 11, 2025 at 7:49 PM
A rare sighting of @csprofkgd.bsky.social, showing his students some cool @vscode.dev productivity hacks.
Ending the #RSS AC meeting on a high note with @mgb45.bsky.social, Rudolf Lioutikov, Jana Tumova, and Abhinav Valada. Can’t wait to see all of you again soon!
April 6, 2025 at 5:50 PM
Ending the #RSS AC meeting on a high note with @mgb45.bsky.social, Rudolf Lioutikov, Jana Tumova, and Abhinav Valada. Can’t wait to see all of you again soon!
Excited to attend the RSS AC meeting for the first time. It’s held at #MIT this year. Great organization by @lucacarlone.bsky.social!
April 4, 2025 at 2:17 PM
Excited to attend the RSS AC meeting for the first time. It’s held at #MIT this year. Great organization by @lucacarlone.bsky.social!
Spotted @csprofkgd.bsky.social trying out his (new?) "AR" glasses at @vectorinstitute.ai. Being a prof in Computer Vision is hard work.
April 1, 2025 at 5:48 PM
Spotted @csprofkgd.bsky.social trying out his (new?) "AR" glasses at @vectorinstitute.ai. Being a prof in Computer Vision is hard work.
When you board the plane, and find your
@uoft.bsky.social CS colleague sitting next to you. Great connecting with you for the first time in person, Bo Wang!
@uoft.bsky.social CS colleague sitting next to you. Great connecting with you for the first time in person, Bo Wang!
March 24, 2025 at 1:58 AM
When you board the plane, and find your
@uoft.bsky.social CS colleague sitting next to you. Great connecting with you for the first time in person, Bo Wang!
@uoft.bsky.social CS colleague sitting next to you. Great connecting with you for the first time in person, Bo Wang!
Our newest "robot" has arrived. 🎉
March 21, 2025 at 8:04 PM
Our newest "robot" has arrived. 🎉
Reposted by Igor Gilitschenski
In case somebody needs older algorithms in a new dress, I open sourced my jax implementation of MBPO. It also contains my own vagram algorithm
github.com/cvoelcker/ja...
github.com/cvoelcker/ja...
GitHub - cvoelcker/jax_mbpo: A jax-based reimplementation of MBPO
A jax-based reimplementation of MBPO. Contribute to cvoelcker/jax_mbpo development by creating an account on GitHub.
github.com
March 18, 2025 at 10:10 PM
In case somebody needs older algorithms in a new dress, I open sourced my jax implementation of MBPO. It also contains my own vagram algorithm
github.com/cvoelcker/ja...
github.com/cvoelcker/ja...
Learning the hard way why people who switched to fish complain that incompatibility to bash can be a real issue. I'd still argue that the benefits outweigh the costs, but maybe this is just my stubbornness.
March 17, 2025 at 8:45 PM
Learning the hard way why people who switched to fish complain that incompatibility to bash can be a real issue. I'd still argue that the benefits outweigh the costs, but maybe this is just my stubbornness.
I am excited to share that my students @kai-he.bsky.social, @yashkant.bsky.social, Ziyi Wu, and Toshiya Yura, our previous research visitor from Sony, will present papers at #CVPR2025. 🎉 Check out their amazing work! 1/🧵
March 3, 2025 at 7:47 PM
I am excited to share that my students @kai-he.bsky.social, @yashkant.bsky.social, Ziyi Wu, and Toshiya Yura, our previous research visitor from Sony, will present papers at #CVPR2025. 🎉 Check out their amazing work! 1/🧵
Reposted by Igor Gilitschenski
In NAVSIM #NeurIPS24, we use simulation metrics for end-to-end driving by unrolling BEV abstractions of scenes for a few seconds. The result? Open-loop evaluation that is better aligned with closed-loop evaluation compared to traditional open loop metrics. github.com/autonomousvi...
February 28, 2025 at 7:22 AM
In NAVSIM #NeurIPS24, we use simulation metrics for end-to-end driving by unrolling BEV abstractions of scenes for a few seconds. The result? Open-loop evaluation that is better aligned with closed-loop evaluation compared to traditional open loop metrics. github.com/autonomousvi...