submit

Submitting a paper to the workshop.

Accepted papers will be part of the conference proceedings. Submission details will be added “soon”.

The final camera-ready deadline for workshop papers as set by ECCV is August 14 2026, any time on earth.

Paper pre-registration

The workshop will have a call for papers on empirical insights, empirical theory, how to do empirical representation learning research, meta-science for representation learning, etc. We are inspired by Hitchens’s razor: What can be asserted without evidence can also be dismissed without evidence and the Troubling Trends in ML scholarship paper (Lipton & Steinhardt, 2019) and others (Greydanus & Kobak, 2024); (Hung et al., 2025); (Picard, 2021); (Sculley et al., 2018) and design the review process accordingly, including questions such as

  • What is interesting about the paper?

  • Explanation vs Speculation: are all claims supported with empirical evidence?

  • Sources of empirical gains: what empirical evidence is there to support that the improved accuracy comes from what is claimed, and not due to some other confounding effect? (e.g. hyper-parameters?)

  • Methodological generalizability: how are the findings relevant to other methods/papers?

We will use paper pre-registration, where a short, templated, research proposal is reviewed, given feedback, and scored on acceptance likelihood if deemed interesting, independent of what findings come out. Additionally, we offer poster boards to relevant work from the main conference, offering authors an additional presentation venue.

 


 

Bibliography

2025

  1. Metascience for machine learning
    Hayley Hung, Marco Loog, and Jan Gemert
    2025

2024

  1. Scaling Down Deep Learning with MNIST-1D
    Samuel James Greydanus and Dmitry Kobak
    In International Conference on Machine Learning, 2024

2021

  1. Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
    David Picard
    ArXiv, 2021

2019

  1. Research for practice: troubling trends in machine-learning scholarship
    Zachary C Lipton and Jacob Steinhardt
    Communications of the ACM, 2019

2018

  1. Winner’s Curse? On Pace, Progress, and Empirical Rigor
    D. Sculley, Jasper Snoek, Alex Wiltschko, and Ali Rahimi
    2018