Francesco Locatello

@FrancescoLocat8

PhD student at ETH Zürich and Max Planck Institute for Intelligent Systems

Vrijeme pridruživanja: lipanj 2018.

Tweetovi

Blokirali ste korisnika/cu @FrancescoLocat8

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @FrancescoLocat8

  1. Prikvačeni tweet

    I'm glad to share that we have received the Best Paper Award!

    Poništi
  2. proslijedio/la je Tweet
    14. sij

    If you are interested in doing a DPhil (ie PhD) with me, please consider applying for either the DPhil in Statistics () or the CDT (). Deadlines for both are 24th January!

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    9. sij

    We are organizing a workshop on Causal learning for Decision Making at along with , Jovana Mitrovic, , Stefan and . Consider submitting your work!

    Poništi
  4. proslijedio/la je Tweet
    10. srp 2019.

    Our new paper on using VAEs to deal with missing data in time series is online! This is joint work with and . Find the link here: Details in the thread.

    Prikaži ovu nit
    Poništi
  5. 6. sij

    Cool new paper from on transfer learning! SOTA performances with a clean pipeline and without obscure tricks

    Poništi
  6. How much supervision do you need to learn disentangled representations? Turns out, not that much! Joint work with , S. Bauer, , and . Accepted at

    Poništi
  7. proslijedio/la je Tweet

    Are disentangled representations helpful for abstract visual reasoning? Come find out later today during the afternoon poster session at 17:00, poster board 28. This is joint work with , , and

    Poništi
  8. 3) Are Disentangled Representations Helpful for Abstract Visual Reasoning? Poster 28. Joint work with , , and If you want to talk to me, I'll be at poster 34! (3/3)

    Prikaži ovu nit
    Poništi
  9. 2) On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset: Poster 35. Joint work with Gondal, Bauer S., , et al. (2/3)

    Prikaži ovu nit
    Poništi
  10. Big disentanglement line-up today 17:00 at ! 1) On the Fairness of Disentangled Representations: Poster 34. Joint work with Abbati G., , Bauer S., and (1/3)

    Prikaži ovu nit
    Poništi
  11. Interested in semidefinite programs? Check out poster 166 at , 17:00 today. With Alp, Olivier and we propose a new efficient stochastic solver for a broad class of non-smooth problems that include SDPs!

    Poništi
  12. proslijedio/la je Tweet

    An update of our paper investigating object compositionality in GANs is now available: We show how a structured generator that learns about objects can facilitate unsupervised instance segmentation. w/ 1/4

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    26. stu 2019.

    A very comprehensive, delightful and inspiring paper. Recommended to ALL, not just MANY ML/AI folks. Note also that does not perceive me as "polarizing the field" as suggested by here: . SCM unifies, invites and educates.

    Poništi
  14. Exciting addition to disentanglement_lib by , and co-authors. Thank you for contributing!

    Poništi
  15. proslijedio/la je Tweet
    15. stu 2019.

    On the Fairness of Disentangled Representations (poster Thu Dec 12th) by , Gabriele Abbati, , Stefan Bauer, with

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    7. stu 2019.

    An update: has been in contact with Canadian immigration officials. They told him that anyone who has been denied a visa to attend can request their case to be reconsidered via this form:   No guarantees, but please pass along!

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    6. stu 2019.

    We’re pleased to release the Visual Task Adaptation Benchmark (VTAB), a diverse, realistic, and challenging protocol to measure progress towards universal visual representations. Learn all about it below.

    Poništi
  18. We propose a Frank-Wolfe variant for stochastic/online optimization of semidefinite programs! Also, Alp just released the code to reproduce our experiments: (2/2)

    Prikaži ovu nit
    Poništi
  19. In the past year I've been mostly focused on disentanglement, but I'm super proud of our paper "Stochastic Frank-Wolfe for Composite Convex Minimization" with Alp Yurtsever, Olivier Fercoq and (1/2)

    Prikaži ovu nit
    Poništi
  20. Joint work with fantastic collaborators Gabriele Abbati, , Stefan Bauer, and from , , , and .

    Prikaži ovu nit
    Poništi
  21. Interested in Fairness and Representation Learning? The code to reproduce our paper “On the Fairness of Disentangled Representations” is now available at

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·