F. Güney
@fguney.bsky.social
research on computer vision, teaching, and movies.
tweets in TR, EN
tweets in TR, EN
while preparing for my ERC interview, I worked with a Turkish designer on my slides.
I loved his work so much that I recommended him to friends, who recommended him to others, and so on.
today he told me he’s been hired for 4 more projects.
your work really does become your reference 😇
I loved his work so much that I recommended him to friends, who recommended him to others, and so on.
today he told me he’s been hired for 4 more projects.
your work really does become your reference 😇
January 27, 2026 at 1:50 PM
while preparing for my ERC interview, I worked with a Turkish designer on my slides.
I loved his work so much that I recommended him to friends, who recommended him to others, and so on.
today he told me he’s been hired for 4 more projects.
your work really does become your reference 😇
I loved his work so much that I recommended him to friends, who recommended him to others, and so on.
today he told me he’s been hired for 4 more projects.
your work really does become your reference 😇
do I have any followers* here who happen to be ELLIS program/unit directors? to become an ELLIS scholar, I need their help with the nomination 🥰
*initially I said friends but then couldn’t stop laughing at the idea of me having friends who happen to be directors 😂
*initially I said friends but then couldn’t stop laughing at the idea of me having friends who happen to be directors 😂
January 24, 2026 at 1:22 PM
do I have any followers* here who happen to be ELLIS program/unit directors? to become an ELLIS scholar, I need their help with the nomination 🥰
*initially I said friends but then couldn’t stop laughing at the idea of me having friends who happen to be directors 😂
*initially I said friends but then couldn’t stop laughing at the idea of me having friends who happen to be directors 😂
Reposted by F. Güney
Our new E2E driving method, TransFuser v6, is out on ArXiv.
It outperforms all other methods on CARLA by a wide margin, 95 DS on Bench2Drive!
We show that minimizing the asymmetry between data annotator and policy is key for strong IL results.
Code, models, and paper:
ln2697.github.io/lead/
It outperforms all other methods on CARLA by a wide margin, 95 DS on Bench2Drive!
We show that minimizing the asymmetry between data annotator and policy is key for strong IL results.
Code, models, and paper:
ln2697.github.io/lead/
December 27, 2025 at 1:42 AM
Our new E2E driving method, TransFuser v6, is out on ArXiv.
It outperforms all other methods on CARLA by a wide margin, 95 DS on Bench2Drive!
We show that minimizing the asymmetry between data annotator and policy is key for strong IL results.
Code, models, and paper:
ln2697.github.io/lead/
It outperforms all other methods on CARLA by a wide margin, 95 DS on Bench2Drive!
We show that minimizing the asymmetry between data annotator and policy is key for strong IL results.
Code, models, and paper:
ln2697.github.io/lead/
do you also feel bad when you realize you’re not only good at non-research tasks, but actually enjoy them?
like… I shouldn’t like report-writing. I should be writing papers.
and yet, talking about our achievements in the first ERC reporting period feels so good!
like… I shouldn’t like report-writing. I should be writing papers.
and yet, talking about our achievements in the first ERC reporting period feels so good!
December 26, 2025 at 6:50 AM
do you also feel bad when you realize you’re not only good at non-research tasks, but actually enjoy them?
like… I shouldn’t like report-writing. I should be writing papers.
and yet, talking about our achievements in the first ERC reporting period feels so good!
like… I shouldn’t like report-writing. I should be writing papers.
and yet, talking about our achievements in the first ERC reporting period feels so good!
“Unlike a camera, which stores with equal resolution each bit of visual information, sight is highly directed. It is focused on capturing relevant information to convey meaning, not fidelity.
…
…
December 25, 2025 at 4:52 PM
“Unlike a camera, which stores with equal resolution each bit of visual information, sight is highly directed. It is focused on capturing relevant information to convey meaning, not fidelity.
…
…
Reposted by F. Güney
The 4th AI for Robotics workshop surfaced converging themes around embodied perception, task learning & evaluation methodologies - emphasising a shift to integrated, context-aware systems. Dive into our key takeaways #AI #Robotics #spatialAI
🥽 ➡️ tinyurl.com/bvxxcn5e
🥽 ➡️ tinyurl.com/bvxxcn5e
Read about the 5 common themes that emerged from the talks and discussions at the 4th edition of this international workshop.
Common themes that emerged from the talks and discussions at the 4th edition of this international workshop.
tinyurl.com
December 23, 2025 at 1:05 PM
The 4th AI for Robotics workshop surfaced converging themes around embodied perception, task learning & evaluation methodologies - emphasising a shift to integrated, context-aware systems. Dive into our key takeaways #AI #Robotics #spatialAI
🥽 ➡️ tinyurl.com/bvxxcn5e
🥽 ➡️ tinyurl.com/bvxxcn5e
The Reith Lectures might be my favourite thing that comes out around this time of year. I’m really enjoying this year’s series, Moral Revolution by Rutger Bregman.
www.bbc.co.uk/programmes/a...
www.bbc.co.uk/programmes/a...
BBC Radio 4 - The Reith Lectures - BBC Reith Lectures 2025 – Moral Revolution
Historian and author Rutger Bregman announced as BBC Radio 4's Reith lecturer for 2025.
www.bbc.co.uk
December 3, 2025 at 12:40 PM
The Reith Lectures might be my favourite thing that comes out around this time of year. I’m really enjoying this year’s series, Moral Revolution by Rutger Bregman.
www.bbc.co.uk/programmes/a...
www.bbc.co.uk/programmes/a...
when you find yourself saying “if you’re old enough to know Fast R-CNN stuff” in a talk 🥹🥹
November 27, 2025 at 10:27 AM
when you find yourself saying “if you’re old enough to know Fast R-CNN stuff” in a talk 🥹🥹
Reposted by F. Güney
Last week’s #AI4Robotics workshop was fab & fabulously full 😊 If you missed out we've good news -
📽️ All 15 talk recordings are now online 🚀! tinyurl.com/4ns5apvd
Catch up on cutting-edge work in #robot perception, action & autonomy - from #SLAM & control to computer vision & large-scale learning!
📽️ All 15 talk recordings are now online 🚀! tinyurl.com/4ns5apvd
Catch up on cutting-edge work in #robot perception, action & autonomy - from #SLAM & control to computer vision & large-scale learning!
November 27, 2025 at 10:04 AM
Last week’s #AI4Robotics workshop was fab & fabulously full 😊 If you missed out we've good news -
📽️ All 15 talk recordings are now online 🚀! tinyurl.com/4ns5apvd
Catch up on cutting-edge work in #robot perception, action & autonomy - from #SLAM & control to computer vision & large-scale learning!
📽️ All 15 talk recordings are now online 🚀! tinyurl.com/4ns5apvd
Catch up on cutting-edge work in #robot perception, action & autonomy - from #SLAM & control to computer vision & large-scale learning!
last year after ECCV in Milano I joked about how expensive Italy felt and a few ppl kindly suggested I explore other parts of the country, so here I am taking the advice!
November 25, 2025 at 7:28 PM
last year after ECCV in Milano I joked about how expensive Italy felt and a few ppl kindly suggested I explore other parts of the country, so here I am taking the advice!
Fatih is presenting our work Mapping like a Skeptic 🔎 tomorrow at #BMVC2025!
paper: arxiv.org/abs/2508.21689
code: github.com/Fatih-Erdoga...
paper: arxiv.org/abs/2508.21689
code: github.com/Fatih-Erdoga...
November 24, 2025 at 8:48 PM
Fatih is presenting our work Mapping like a Skeptic 🔎 tomorrow at #BMVC2025!
paper: arxiv.org/abs/2508.21689
code: github.com/Fatih-Erdoga...
paper: arxiv.org/abs/2508.21689
code: github.com/Fatih-Erdoga...
what a nice way to end an amazing 2-day workshop in Grenoble 😊
November 21, 2025 at 9:05 PM
what a nice way to end an amazing 2-day workshop in Grenoble 😊
just wanted to clarify that we always try to report results (for sure for main results, maybe not all ablations) over 3 runs* for online evaluations as mean and std. maybe it was a mistake to show barplots without mentioning this.
*probably not enough but still better than reporting only one run.
*probably not enough but still better than reporting only one run.
November 21, 2025 at 3:32 PM
just wanted to clarify that we always try to report results (for sure for main results, maybe not all ablations) over 3 runs* for online evaluations as mean and std. maybe it was a mistake to show barplots without mentioning this.
*probably not enough but still better than reporting only one run.
*probably not enough but still better than reporting only one run.
Reposted by F. Güney
Andrea Vedaldi talks about 4D reconstruction, leveraging 4D generation, but also representations based on dynamic point maps which encode points for different viewpoints AND different time steps.
AI 4 Robotics workshop at @naverlabseurope.bsky.social
AI 4 Robotics workshop at @naverlabseurope.bsky.social
November 20, 2025 at 11:21 AM
Andrea Vedaldi talks about 4D reconstruction, leveraging 4D generation, but also representations based on dynamic point maps which encode points for different viewpoints AND different time steps.
AI 4 Robotics workshop at @naverlabseurope.bsky.social
AI 4 Robotics workshop at @naverlabseurope.bsky.social
Reposted by F. Güney
Fatma Guney on thinking fast and slow for autonomous driving: how to combine bigger models with higher latency with smaller models with lower latency by forecasting rich but stale features to the future.
AI 4 Robotics Workshop at @naverlabseurope.bsky.social
AI 4 Robotics Workshop at @naverlabseurope.bsky.social
November 20, 2025 at 2:40 PM
Fatma Guney on thinking fast and slow for autonomous driving: how to combine bigger models with higher latency with smaller models with lower latency by forecasting rich but stale features to the future.
AI 4 Robotics Workshop at @naverlabseurope.bsky.social
AI 4 Robotics Workshop at @naverlabseurope.bsky.social
EuroHPC wrote a piece about our love of GPUs 😊
A EuroHPC Success Story | Clear Vision for Self-Driving Cars
www.eurohpc-ju.europa.eu/eurohpc-succ...
A EuroHPC Success Story | Clear Vision for Self-Driving Cars
www.eurohpc-ju.europa.eu/eurohpc-succ...
October 23, 2025 at 12:00 PM
EuroHPC wrote a piece about our love of GPUs 😊
A EuroHPC Success Story | Clear Vision for Self-Driving Cars
www.eurohpc-ju.europa.eu/eurohpc-succ...
A EuroHPC Success Story | Clear Vision for Self-Driving Cars
www.eurohpc-ju.europa.eu/eurohpc-succ...
Reposted by F. Güney
Track-On2: Enhancing Online Point Tracking with Memory
By Görkay Aydemir, Weidi Xie, @fguney.bsky.social
TLDR: explicit memory for point tracking, holds decoder features, similar to what MUSt3R does for reconstruction.
arxiv.org/abs/2509.19115
By Görkay Aydemir, Weidi Xie, @fguney.bsky.social
TLDR: explicit memory for point tracking, holds decoder features, similar to what MUSt3R does for reconstruction.
arxiv.org/abs/2509.19115
September 24, 2025 at 6:47 AM
Track-On2: Enhancing Online Point Tracking with Memory
By Görkay Aydemir, Weidi Xie, @fguney.bsky.social
TLDR: explicit memory for point tracking, holds decoder features, similar to what MUSt3R does for reconstruction.
arxiv.org/abs/2509.19115
By Görkay Aydemir, Weidi Xie, @fguney.bsky.social
TLDR: explicit memory for point tracking, holds decoder features, similar to what MUSt3R does for reconstruction.
arxiv.org/abs/2509.19115
Reposted by F. Güney
Our Autonomous Systems workshop series is back for its 3rd edition at CVPR 2025! Remember the queue in Seattle? Please mark the workshop in your CVPR registration so we have enough space this year! opendrivelab.com/cvpr2025/wor...
April 19, 2025 at 5:55 PM
Our Autonomous Systems workshop series is back for its 3rd edition at CVPR 2025! Remember the queue in Seattle? Please mark the workshop in your CVPR registration so we have enough space this year! opendrivelab.com/cvpr2025/wor...
Reposted by F. Güney
Our Workshop on Uncertainty Quantification for Computer Vision goes to @cvprconference.bsky.social this year!
We have a super line-up of speakers and a call for papers.
This is a chance for your paper to shine at #CVPR2025
⏲️ Submission deadline: 14 March
💻 Page: uncertainty-cv.github.io/2025/
We have a super line-up of speakers and a call for papers.
This is a chance for your paper to shine at #CVPR2025
⏲️ Submission deadline: 14 March
💻 Page: uncertainty-cv.github.io/2025/
February 28, 2025 at 7:28 AM
Our Workshop on Uncertainty Quantification for Computer Vision goes to @cvprconference.bsky.social this year!
We have a super line-up of speakers and a call for papers.
This is a chance for your paper to shine at #CVPR2025
⏲️ Submission deadline: 14 March
💻 Page: uncertainty-cv.github.io/2025/
We have a super line-up of speakers and a call for papers.
This is a chance for your paper to shine at #CVPR2025
⏲️ Submission deadline: 14 March
💻 Page: uncertainty-cv.github.io/2025/
feel free to nominate yourself or anyone else at KUIS AI talks: forms.gle/nbqhKsWbC9Swoqzi8
KUIS AI Talks Speaker Nomination Form
KUIS AI was established in 2020 jointly by Koç University and Is Bank. With its 17 AI faculty, 23 affiliated faculty from the schools of engineering, medicine, science, and other fields, and over 100 ...
forms.gle
February 18, 2025 at 6:53 AM
feel free to nominate yourself or anyone else at KUIS AI talks: forms.gle/nbqhKsWbC9Swoqzi8
agreed. one of the messages from his talk is studying statistics, computer science, and economics together. I find his perspective on AI very realistic.
also, how he changed the direction of discussion on bias during the panel in the end, should be studied in textbooks.
also, how he changed the direction of discussion on bias during the panel in the end, should be studied in textbooks.
Michael Jordan's talk on the multi-agent and micro-econ perspective on AI and how we need a new vision of the future is killer:
www.youtube.com/live/W0QLq4q...
www.youtube.com/live/W0QLq4q...
AI, Science and Society Conference - AI ACTION SUMMIT - DAY 1
YouTube video by IP Paris
www.youtube.com
February 9, 2025 at 9:01 PM
agreed. one of the messages from his talk is studying statistics, computer science, and economics together. I find his perspective on AI very realistic.
also, how he changed the direction of discussion on bias during the panel in the end, should be studied in textbooks.
also, how he changed the direction of discussion on bias during the panel in the end, should be studied in textbooks.
in a privileged setting, RL with self-play seems to be the answer to planning for driving. impressive to see complex behavior learning without supervision and zero-shot generalization across benchmarks by GigaFlow. the next question is what about with perception, is it just a matter of computation?
February 9, 2025 at 12:18 PM
in a privileged setting, RL with self-play seems to be the answer to planning for driving. impressive to see complex behavior learning without supervision and zero-shot generalization across benchmarks by GigaFlow. the next question is what about with perception, is it just a matter of computation?
“..unsere heimat wieder gross”
I wish my German was not enough to understand this, what the hell is happening to Germany 🥹🥹
I wish my German was not enough to understand this, what the hell is happening to Germany 🥹🥹
February 4, 2025 at 1:26 PM
“..unsere heimat wieder gross”
I wish my German was not enough to understand this, what the hell is happening to Germany 🥹🥹
I wish my German was not enough to understand this, what the hell is happening to Germany 🥹🥹
since Görkay came up with Track-On, we've been waiting for this day:
Track with me, if it's just for the frame, maybe tomorrow, the occlusion will take you away! 🎵🎸😶🌫️
Happy to introduce our #ICLR2025 paper
"Track-On: Transformer-based Online Point Tracking with Memory": kuis-ai.github.io/track_on/
Track with me, if it's just for the frame, maybe tomorrow, the occlusion will take you away! 🎵🎸😶🌫️
Happy to introduce our #ICLR2025 paper
"Track-On: Transformer-based Online Point Tracking with Memory": kuis-ai.github.io/track_on/
Track-On
Track-On
kuis-ai.github.io
February 3, 2025 at 8:25 AM
since Görkay came up with Track-On, we've been waiting for this day:
Track with me, if it's just for the frame, maybe tomorrow, the occlusion will take you away! 🎵🎸😶🌫️
Happy to introduce our #ICLR2025 paper
"Track-On: Transformer-based Online Point Tracking with Memory": kuis-ai.github.io/track_on/
Track with me, if it's just for the frame, maybe tomorrow, the occlusion will take you away! 🎵🎸😶🌫️
Happy to introduce our #ICLR2025 paper
"Track-On: Transformer-based Online Point Tracking with Memory": kuis-ai.github.io/track_on/
open-source, open-weight, I'll take whichever because, unlike the ones who share nothing, a few at least make an effort and change the game for everyone.
I expect the effect of open stuff like Cosmos to be huge on physical AI. we are already trying it. also downloaded the DeepSeek, we shall see 🤞
I expect the effect of open stuff like Cosmos to be huge on physical AI. we are already trying it. also downloaded the DeepSeek, we shall see 🤞
January 30, 2025 at 6:39 AM
open-source, open-weight, I'll take whichever because, unlike the ones who share nothing, a few at least make an effort and change the game for everyone.
I expect the effect of open stuff like Cosmos to be huge on physical AI. we are already trying it. also downloaded the DeepSeek, we shall see 🤞
I expect the effect of open stuff like Cosmos to be huge on physical AI. we are already trying it. also downloaded the DeepSeek, we shall see 🤞