1. X
  2. Christian Wolf (🦋🦋🦋)
Log inSign up
Christian Wolf (🦋🦋🦋)
5,858 posts
Image
user avatar
Christian Wolf (🦋🦋🦋)
@chriswolfvision
Principal Scientist, @NaverLabsEurope, Lead of Spatial AI team. AI for Robotics. Feedback: admonymous.co/chriswolfvision
Lyon, France
chriswolfvision.github.io/www
Joined November 2015
747
Following
8,464
Followers
RepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Mar 23, 2023
    How can one get the tweets of AI research folks but not the tweets of AI influencers? Asking for a friend.
    140K
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Oct 3, 2020
    That's a nice way of writing equations (I sometimes do this in lectures). From ICLR 2021 submission ("An attention free transformer"), openreview.net/forum?id=pW--c…
    Image
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Nov 29, 2020
    I passed this image through a pretrained ResNet 101 with @PyTorch and it predicts: Tiger shark 23% Hammerhead 21% Great white shark 16% Gar, garfish 11% Sturgeon 3% My conclusion : shape > [ texture + mountain context] => reassuring in some way. (Image from @SolTight)
    Image
    This Post is from an account that no longer exists. Learn more
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Jun 13, 2024
    This is on of the best papers I have recently read, congrats for this excellent work. "NNs do not have an inherent “simplicity bias”. This property depends on components such as ReLUs, residual connections, and layer normalizations". This also applies to transformers.
    Image
    Image
    user avatar
    Damien Teney
    @DamienTeney
    Jun 12, 2024
    Replying to @francoisfleuret
    Whatever signal has the same shape as that preferred by your architecture (shameless plug: Neural Redshift arxiv.org/abs/2403.02241).
    78K
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    May 31, 2021
    Peak AI happened finally ... #NeurIPS2021 "We received 9,052 full paper submissions this year, a slight decrease compared to last year."
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Oct 5, 2020
    I trained a CNN w/o pooling on MNIST and produced a colored visualization of the feature maps you get when you translate a digit on an input canvas. This illustrates the equivariance property of convolutions. More info (why convolutions?) in a blog post: medium.com/@chriswolfvisi…
    Image
    GIF
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Mar 10, 2023
    Just created a new Figure for a survey paper, I am quite satisfied.
    Image
    82K
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Jan 24, 2021
    I love this figure showing the difference of manifolds learned by GANs and VAEs on a 1D toy example. The VAE learns the mean, the GAN passes through the data with higher fidelity but does not cover the full domain. From: Plumerault et al. ICPR 2020 arxiv.org/abs/2012.11551
    Image
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Jun 20, 2024
    This paper had been rejected 4x at conferences and now got the #cvpr2024 best student paper runner up reward! arxiv.org/abs/2212.06872
    Image
    55K
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Oct 14, 2024
    I can fix computers only if they have a tape of infinite length.
    13K
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    May 16, 2023
    Integral neural networks look like a fantastic innovation: continuous representations along filter and channel dimension, prune w/o finetuning. It is rare to discover a paper when the #CVPR proceedings are published, this paper was not on arxiv before.. openaccess.thecvf.com/content/CVPR20…
    Image
    73K
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Jan 9, 2022
    This new Biography of John von Neumann was an incredible read. I am not sure he was really human... The book is extremely well written and puts all his ideas and work into its historical context, eg the work of Turing and Gödel, and follow-up work, eg Conway etc.
    Image
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Mar 21, 2021
    A thread on similarities in the ways the field addressed two seemingly different problems, namely A) recent work on transformers / self-attention addressing their quadratic complexity, and B) work decoupling capacity and memory size in recurrent neural networks. 👇 1/19
    Image
  • user avatar
    Christian Wolf (🦋🦋🦋)
    @chriswolfvision
    Nov 11, 2023
    < 2018: we have tried instance norm, batch norm, layer norm ... 2018: let's normalize over the missing dim, channel groups => ECCV 2018 best paper < 2023: we applied the Fourier transform over 1d signals, images, time .... 2023: let's FFT channels => ICLR ratings of 8, 8, 10, 8.
    Image
    Image
    user avatar
    Peyman Milanfar
    @docmilanfar
    Nov 11, 2023
    How do you get the highest ICLR ‘24 review scores (8, 8, 10, 8) ? You revitalize your old course notes for Image Processing 101.
    100K
Advertisement
Advertisement