@YaoQinUCSD , @colinraffel ,Sara Sabour , Gary Cottrell, Geoffrey Hinton and I have released a full version of our workshop paper on capsule networks and adversarial attack detection! Check it out, or read this thread if you are busy :) 1/7 arxiv.org/pdf/1907.02957…

#mlss kicked off today at #skoltech with a great session on optimal transport and nice applications to image data

#MLSS #Skoltech group photo

One of the highlights this week is a few days of lectures and tutorials on #ReinforcementLearning by Shimon Whiteson from University of Oxford at the MLSS 2019. #MachineLearning #DataScience

„Data science and machine learning conferences (NeurIPS, ICML, AISTATS, ICLR, UAI, ...): Allow remote paper & poster presentations at conferences” - chng.it/BNdfwrg6

Check out our Python 3 toolbox for alpha matting: github.com/pymatting/pyma… Any feedback is welcome! Feel free to post issues or pull-requests! #imageprocessing #python

Our alpha matting library PyMatting has been accepted for publication in the Journal of Open Source Software! 🎉

We are presenting our poster „Phase Retrieval Using Conditional Generative Adversarial Networks“ at virtual icpr2020milan today! See you at poster session T5.4! This is joint work with Alexander Oberstraß and Stefan Harmeling. paper: arxiv.org/pdf/1912.04981…

Great podcast about PyTorch's development by Edward Z. Yang! 👍🏼

Wrote a tiny summary of our ICLR paper and some thoughts on trade-off conditional policies for adaptivity in general :) medium.com/@p.swazinna/co…

We wrote a survey on self-supervised representation learning that summarizes the recent methods 🎉 Feedback welcome! arxiv.org/abs/2308.11455

Consider submitting to our NeurIPS 2023 workshop on failure modes of foundation models! 📝 The deadline has been extended to October 4th 🗓️

#NeurIPS2023 Gear up for a rollercoaster ride of AI misadventures at 'Failure Modes in the Age of Foundation Models'! 🤖🎢Join our workshop tomorrow in room R02 for fun tales of AI gone wild, quirky biases, and epic fails. #ICBINBworkshop sites.google.com/view/icbinb-20…

Organizing the ICBINB workshop with these wonderful people was an awesome experience! I am looking forward to the next edition! 🥳

Excited to announce that our workshop "I Can't Believe It's Not Better: Challenges in Applied Deep Learning" has been accepted at #ICLR2025! 🎉 Stay tuned for updates on the agenda, and paper submissions.

ICLR 2025 starts next week! Our workshop “I Can’t Believe It’s Not Better” is on April 28 (Singapore time) — join us to talk real-world challenges in applying deep learning and foundation models across fields. 📍 iclr.cc/virtual/2025/w…

Yesterday's trip to Venice