Apostolos Modas (@amodas_) profile picture

Senior AI Engineer | Applied Scientist @SonyAI_global | PhD from @EPFL 🇹🇭

Lausanne, Switzerland
Joined July 2020
Photo by Apostolos Modas (@amodas_)
Our work has been published in @Nature ! 🎉🎉 FHIBE redefines ethical data collection and pushes fairness benchmarks forward in human-centric computer vision. A massive congrats to the whole team! 👏 Paper: nature.com/articles/s41586-0
 #FHIBE #Nature
4
71
Apostolos Modas retweeted
Nature research paper: Fair human-centric image dataset for ethical AI benchmarking go.nature.com/4hSUagA
10
3
31
17,644
Apostolos Modas retweeted
Glad to have two papers accepted to #EMNLP2024 as main! 🎉 1) "Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes" arxiv.org/abs/2407.03623 w/ Jerone Andrews, @dorazhao9, @SciOrestis, @amodas_, @YutaNakashima4, @alicexiang đŸ§”1/2
5
8
64
6,816
Do you want to learn more about ethical and responsible image data collection? Then come find us at #NeurIPS2023 đŸ€“ Oral: Thu. 10:30 CST (Oral 5B) 🚀 Poster #1602: Thu. 10:45 CST (Poster session 5) đŸ‘šâ€đŸ’Œ
6
306
Are you amazed by weight interpolation techniques to edit large pre-trained models? đŸ€” Then you’re going to love our work 🚀: “Task Arithmetic in the Tangent Space”🏄 which explains why they work and gives a simple way to make them better! đŸ€“ 📄: rb.gy/q9djm đŸ§”1/9
7
110
4
536
82,636
Are you amazed by NeRFs, SIRENs or FFNs but don’t know why they work? đŸ€” Then you’re going to love our work 🚀: “A structured dictionary perspective on implicit neural representations” @CVPR which explains how INRs manage to look so crisp! đŸ€“ 📄: https://xitter.cf/t.co/29uNJrKap8 đŸ§” 1/9
4
153
10
678
Apostolos Modas retweeted
If you can donate money to support Ukraine now, here are some vetted funds 👇
1
59
7
123
"Deep nets are commonly believed to always converge to the simplest possible solution. This study elegantly demonstrates that they sometimes prefer complex solutions to simple ones, depending on the inductive biases in their architecture" ~Review by Anon rentry.co/rev_fs_0002
1
2
1
4
Apostolos Modas retweeted
When there exist multiple valid solutions for a given task, do neural networks always go for the “simplest” one? with @gortizji, @ItamarSalazar, @modasapo and @pafrossard. Happy to hear your thoughts on that :)
3
2
19
Apparently adversarial robustness improves transfer learning even in non-trivial classification tasks!🧐 Check our new paper "Improving filling level classification with adversarial training" đŸ·đŸ„ƒ 📄arXiv: https://xitter.cf/t.co/OhQCLyrWEB @pafrossard @smartcameras @aXompi @RicSanMat
4
1
19
Hours of thorough and hard work, now published in the Proceedings of IEEE đŸ’ŁđŸ„ł Many credits to my collaborators @gortizji @smoosavid @pafrossard! đŸ’Ș
Interested in adv. robustness beyond security, or how adv. examples can help us understand deep learning? đŸ€” Check our review paper “Optimism in the face of adversity”, just published in the Proc. IEEE 🚀 💎Xplore: https://xitter.cf/t.co/4WaL6OZIuT 📄arXiv: https://xitter.cf/t.co/x8BnM17mle
1
6
A huge DenseNet vs an old-fashioned Logistic Regression, solving a linearly separable problem. Who is gonna win??
Why do state-of-the-art NNs only generalise on a few linearly separable problems? đŸ€“ Figure it out at our poster today at 6-8pm CET (9-11am PST) @ Town E1, spot D3 #NeurIPS2020 🏡 Gather town: https://xitter.cf/t.co/DlnnZsU4Lu
2
6
Our framework provides a geometric connection between adversarial examples and data features! Find us today 6-8pm CET (9-11am PST) @ Town A0, spot A0. #NeurIPS2020
Want to know what happens when you train a CNN on frequency reversed samples and what this has to do with robustness? Then join us at our poster in #NeurIPS2020 đŸ€“ “Hold me tight! Influence of discriminative features on deep network boundaries” 📄: https://xitter.cf/t.co/tApRCvijDB
2
5
Nicolas Flammarion is looking for #PhD student. Find out more about his #research epfl.ch/labs/tml/, and learn more about our @EPFL #EDIC #computerscience PhD program: go.epfl.ch/phd-edic
15
43
Our new "tutorial" on what we've learned from adversarial robustness beyond security is online! Still a pre-print, so any comment/criticism is more than welcome! :) With @gortizji, @smoosavid, @pafrossard
Seeing the glass as half fullđŸ„›Optimism in the Face of Adversity arxiv.org/pdf/2010.09624v1.p
 In this pre-print we talk about what adv. examples reveal about the geometry of deep nets and how other topics in ML can benefit from such insights. With @gortizji , @modasapo, @pafrossard
6
Very excited with the new blog post of our NeurIPS 2020 paper “Neural Anisotropy Directions” where we study the role of architecture in deep learning. Co-authors: @modasapo, @smoosavid and @pafrossard. đŸ’» Blog: https://xitter.cf/t.co/eC1pRyWzkV 📄 Paper: https://xitter.cf/t.co/o7RrW7n8OY 1/n
3
34
7
98
If you are interested to know how ”Redundant features can hurt robustness to distribution shift” check out our virtual poster at ICML'20 UDL Workshop. This is joint work with @ApostolosModas, @smoosavid and @pafrossard. 📄 Paper: https://xitter.cf/t.co/XDqVZatZQy (1/11)
1
6
1
16