Sid
@sidgairo18.bsky.social
🏔️📍🇩🇪
🇪🇺 PhD student at the Max Planck Institute for Informatics, and Institute of Science & Technology - Austria.
💻🏃🏻♂️🚴🏻🏋🏻🏊⛷️🎸🎹📚
Webpage: https://sidgairo18.github.io/
🇪🇺 PhD student at the Max Planck Institute for Informatics, and Institute of Science & Technology - Austria.
💻🏃🏻♂️🚴🏻🏋🏻🏊⛷️🎸🎹📚
Webpage: https://sidgairo18.github.io/
Reposted by Sid
ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇
October 19, 2025 at 7:49 AM
ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇
Heading to #ICCV2025? Don’t miss #CV4DC — Oct 19, Honolulu 🌺 An in-person workshop spotlighting research for/with developing regions.
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
October 9, 2025 at 8:58 PM
Heading to #ICCV2025? Don’t miss #CV4DC — Oct 19, Honolulu 🌺 An in-person workshop spotlighting research for/with developing regions.
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
See exciting keynote talks from leading researches!
See accepted papers & posters here: cv4dc.github.io/2025/
#AI4Good
🌟Here are some resources and notes about doing research that I’ve been compiling since I started my PhD.🌟
I rely on these often, and after sharing them with a few folks in my group who found them useful, I thought it could be of use to the broader community 🧵👇 (1/n)
I rely on these often, and after sharing them with a few folks in my group who found them useful, I thought it could be of use to the broader community 🧵👇 (1/n)
August 12, 2025 at 2:10 PM
🌟Here are some resources and notes about doing research that I’ve been compiling since I started my PhD.🌟
I rely on these often, and after sharing them with a few folks in my group who found them useful, I thought it could be of use to the broader community 🧵👇 (1/n)
I rely on these often, and after sharing them with a few folks in my group who found them useful, I thought it could be of use to the broader community 🧵👇 (1/n)
⏳Still need to wait for your last experiment results?
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
July 24, 2025 at 6:20 AM
⏳Still need to wait for your last experiment results?
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
📣 We're pleased to announce that the deadline for non-proceeding track #CV4DC at @iccv.bsky.social has been extended to August 15, 2025
Looking forward to your submissions! cv4dc.github.io/2025/
Reposted by Sid
Reposted by Sid
Papers being presented from our group at #ICML2025!
Congratulations to all the authors! To know more, visit us in the poster sessions!
A 🧵with more details:
@icmlconf.bsky.social @mpi-inf.mpg.de
Congratulations to all the authors! To know more, visit us in the poster sessions!
A 🧵with more details:
@icmlconf.bsky.social @mpi-inf.mpg.de
July 13, 2025 at 8:00 AM
Papers being presented from our group at #ICML2025!
Congratulations to all the authors! To know more, visit us in the poster sessions!
A 🧵with more details:
@icmlconf.bsky.social @mpi-inf.mpg.de
Congratulations to all the authors! To know more, visit us in the poster sessions!
A 🧵with more details:
@icmlconf.bsky.social @mpi-inf.mpg.de
📣 Proceeding track's results are out.
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
July 12, 2025 at 9:11 AM
📣 Proceeding track's results are out.
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
🎉 Congratulations to all the authors whose papers were accepted. We can't wait to meet you at @iccv.bsky.social in Hawaii on Oct 19th.
⏰ Our non-proceeding track is still accepting submissions until July 20th! Details in the comments
Porto, Portugal 🇵🇹 June-July 2025
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
July 2, 2025 at 8:20 AM
Porto, Portugal 🇵🇹 June-July 2025
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
One of the prettiest and liveliest cities I’ve traveled to ✨ 🚤
🚨More tiny experiments that seem benign: linear probing on frozen features (but again not explicitly making BatchNorm params to .eval) can have big implications.
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
June 23, 2025 at 4:27 PM
🚨More tiny experiments that seem benign: linear probing on frozen features (but again not explicitly making BatchNorm params to .eval) can have big implications.
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
Best test accuracy: 71.20% at Epoch 10, for Learning Rate = 0.01 Makes a hell of a lot of difference! Almost 10% 🚨
Seemingly innocuous error that I see students making time and again: model.eval() or param.eval() for models with norm layers (like batch-norm) is critical. Especially when freezing ❄️ certain layers and training rest.
June 23, 2025 at 2:32 PM
Seemingly innocuous error that I see students making time and again: model.eval() or param.eval() for models with norm layers (like batch-norm) is critical. Especially when freezing ❄️ certain layers and training rest.
Classic fM is a gem to listen to great ensembles of classical music, and also get to experience the old-school radio fM vibes ✨
www.globalplayer.com
www.globalplayer.com
Global Player | Radio, Podcasts, Playlists and Videos
Enjoy all of Global’s radio brands, award-winning podcasts, exclusive videos and expertly-curated playlists, all in one place. Just sign in and enjoy!
www.globalplayer.com
June 22, 2025 at 1:59 PM
Classic fM is a gem to listen to great ensembles of classical music, and also get to experience the old-school radio fM vibes ✨
www.globalplayer.com
www.globalplayer.com
Reposted by Sid
🎉 Exciting News #CVPR2025!
We’re proud to announce that we have 5 papers accepted to the main conference and 7 papers accepted at various CVPR workshops this year!
We’re looking forward to sharing our research with the community in Nashville!
Stay tuned for more details! @mpi-inf.mpg.de
We’re proud to announce that we have 5 papers accepted to the main conference and 7 papers accepted at various CVPR workshops this year!
We’re looking forward to sharing our research with the community in Nashville!
Stay tuned for more details! @mpi-inf.mpg.de
June 11, 2025 at 11:48 AM
🎉 Exciting News #CVPR2025!
We’re proud to announce that we have 5 papers accepted to the main conference and 7 papers accepted at various CVPR workshops this year!
We’re looking forward to sharing our research with the community in Nashville!
Stay tuned for more details! @mpi-inf.mpg.de
We’re proud to announce that we have 5 papers accepted to the main conference and 7 papers accepted at various CVPR workshops this year!
We’re looking forward to sharing our research with the community in Nashville!
Stay tuned for more details! @mpi-inf.mpg.de
Had my older MTB catching dust in the bike room, took 2 hours to replace both tyres and tubes with brand new ones, new brakes, and chain cleaned + greased. 💥
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
May 15, 2025 at 9:00 PM
Had my older MTB catching dust in the bike room, took 2 hours to replace both tyres and tubes with brand new ones, new brakes, and chain cleaned + greased. 💥
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
Pretty relaxing and a nice rejuvinating break from research✨
P.S.: Once you are used to driving road bikes, MTBs seem too slow 🤪
Wow 🤯
So I have now read the Big Three Ayn Rand Books, atlas shrugged, the fountainhead, and anthem. And I have this to say: she’s bad at writing books, so bad, in fact, that I find her popularity genuinely strange
May 15, 2025 at 12:24 AM
Wow 🤯
Had a great time presenting our work at ICLR 2025 in Singapore 🇸🇬.
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
May 4, 2025 at 9:22 AM
Had a great time presenting our work at ICLR 2025 in Singapore 🇸🇬.
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
Lot of great interactions, meeting amazing people and a very well organised conference 🌟.
It was great to catch up with old colleagues and meet new folks.
For more detail see: arxiv.org/abs/2503.00641
🚀 I will be @iclr_conf in Singapore next week presenting our recent work.
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
April 16, 2025 at 10:28 AM
🚀 I will be @iclr_conf in Singapore next week presenting our recent work.
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
We answer how exactly does "What you explain depend on how you train". 🤓
We will be @ Hall 3 + Hall 2B #492 (26th April, 3PM - 5:30 PM)
Please reach out via dm if interestd in a chat or ☕️
#ICLR2025
Reposted by Sid
Congratulations to Max Losch for successfully defending his PhD! 🥳🎉🎓
In his thesis, "Improving Trustworthiness of Deep Learning via Inspectable and Robust Representations", he explores transparency and robustness of deep networks. We wish him the best!
In his thesis, "Improving Trustworthiness of Deep Learning via Inspectable and Robust Representations", he explores transparency and robustness of deep networks. We wish him the best!
April 11, 2025 at 9:14 PM
Congratulations to Max Losch for successfully defending his PhD! 🥳🎉🎓
In his thesis, "Improving Trustworthiness of Deep Learning via Inspectable and Robust Representations", he explores transparency and robustness of deep networks. We wish him the best!
In his thesis, "Improving Trustworthiness of Deep Learning via Inspectable and Robust Representations", he explores transparency and robustness of deep networks. We wish him the best!
Reposted by Sid
Reminder that semantic segmentation evaluation numbers are dependent on the image resolution…but less than one may think (see 4x and 8x downsampling results.
Source: “Fully Convolutional Networks for Semantic Segmentation”
arxiv.org/abs/1411.403...
Source: “Fully Convolutional Networks for Semantic Segmentation”
arxiv.org/abs/1411.403...
April 13, 2025 at 2:42 PM
Reminder that semantic segmentation evaluation numbers are dependent on the image resolution…but less than one may think (see 4x and 8x downsampling results.
Source: “Fully Convolutional Networks for Semantic Segmentation”
arxiv.org/abs/1411.403...
Source: “Fully Convolutional Networks for Semantic Segmentation”
arxiv.org/abs/1411.403...
Reposted by Sid
Hello world, we are now on Bluesky 🦋! Follow us to receive updates on exciting research and projects from our group!
#computervision #machinelearning #research
#computervision #machinelearning #research
April 9, 2025 at 1:03 PM
Hello world, we are now on Bluesky 🦋! Follow us to receive updates on exciting research and projects from our group!
#computervision #machinelearning #research
#computervision #machinelearning #research
Reposted by Sid
So far, 2,135 people have responded to the poll Søren and I posted a few days ago. Of those, 94.4% replied “Yes” to being interested in officially presenting accepted @neuripsconf.bsky.social papers in Europe. (1/7)
April 3, 2025 at 11:03 AM
So far, 2,135 people have responded to the poll Søren and I posted a few days ago. Of those, 94.4% replied “Yes” to being interested in officially presenting accepted @neuripsconf.bsky.social papers in Europe. (1/7)
With systems like PaperBench -the reproducibility tracks at conferences will now also have AI participants 😃😉
Infact, (soonish) the reviewing process could be supported with pipelines that can authenticate claims and results made in papers. 🤓
openai.com/index/paperb...
Infact, (soonish) the reviewing process could be supported with pipelines that can authenticate claims and results made in papers. 🤓
openai.com/index/paperb...
PaperBench: Evaluating AI’s Ability to Replicate AI Research
We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.
openai.com
April 3, 2025 at 1:38 PM
With systems like PaperBench -the reproducibility tracks at conferences will now also have AI participants 😃😉
Infact, (soonish) the reviewing process could be supported with pipelines that can authenticate claims and results made in papers. 🤓
openai.com/index/paperb...
Infact, (soonish) the reviewing process could be supported with pipelines that can authenticate claims and results made in papers. 🤓
openai.com/index/paperb...