Jakub Tomczak

@jmtomczak

Assistant Professor at Vrije Universiteit Amsterdam | Formerly MSC-IF in Max Welling's group at UvA and DL Researcher at Qualcomm | Opinions my own.

Amsterdam, the Netherlands
Vrijeme pridruživanja: listopad 2016.

Tweetovi

Blokirali ste korisnika/cu @jmtomczak

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

  1. proslijedio/la je Tweet
    2. velj

    Learning Discrete Distributions by Dequantization.

    Poništi
  2. proslijedio/la je Tweet
    31. sij

    Learning Discrete Distributions by Dequantization.

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    Very excited to share "Learning Discrete Distributions by Dequantization" () in collaboration with and , from my internship at . We explore different methods and distributions for dequantization and reach 3.06 bpd on CIFAR10.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    31. sij

    In short there are two distributions: the dequantizing distribution q(v|x) and the density model p(v). In this paper we analyse how these distributions interact. Especially take a look at (c), which is the same density model from the previous figure, with a flow as dequantizer.

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    31. sij

    This is an extension of very cool work by J. Ho et al () and et al (). Digital media is generally discrete. The likelihood of continuous distributions can be arbitrarily high (a). Instead we add noise to dequantize (b).

    Prikaži ovu nit
    Poništi
  6. 23. sij

    My first experience with evolutionary robotics 🙉 Learning a neural-network-based controller of a robot with evolvable morphology. A great outcome from a collaboration with , , Fuda, and ! The arXiv version:

    Poništi
  7. proslijedio/la je Tweet
    3. sij

    What better way to start a new year than by applying for a great tenure track position in a great city (Amsterdam) in a great team: AI systems that collaborate with people instead of replacing them: (closes in 3 days).

    Poništi
  8. proslijedio/la je Tweet
    22. pro 2019.

    Really exciting to have my first paper accepted at ! It provides the first group theoretical approach towards equivariant visual attention. Nice things coming up next! . Co-Attentive Equivariant Nets:

    Poništi
  9. proslijedio/la je Tweet

    Happy to share that our paper "Batch-shaping for learning conditional channel gated networks" has been accepted at Paper:  Joint work with &

    Poništi
  10. proslijedio/la je Tweet
    11. pro 2019.

    VAEs enthusiasts, if you are at you should come to poster 110 today at 10.45. We'll be presenting BIVA, and show you how to build powerful deep hierarchical VAEs.  Paper:

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    8. pro 2019.

    Curious about how to generate bike trips? Check presentation "Generation of Human-Like Movements Based on Environmental Features" @ IEEE SSCI 2019 Xiamen

    Poništi
  12. proslijedio/la je Tweet
    8. pro 2019.

    Want to understand how to evolve robot predators? just presented us how: "Simulated and Real-world Evolution of Predator Robots" @ IEEE SSCI 2019

    Poništi
  13. proslijedio/la je Tweet
    6. pro 2019.

    Check out our extensive review paper on normalizing flows! This paper is the product of years of thinking about flows: it contains everything we know about them, and many new insights. With , , , . Thread 👇

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    6. pro 2019.

    Looking for something to read in your flight to ? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) with

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    1. pro 2019.

    Huge congratulations to Patrick Putzky and the rest of our team for winning the “single coil” track! I am very proud!

    Poništi
  16. proslijedio/la je Tweet

    Postdoc positions available at ETH Zurich Foundations of Data Science initiative:

    Poništi
  17. 26. stu 2019.

    I had a great pleasure to give a talk next to , M. Jankowiak, J. Sivic, , A. Grabska-Garbinska, , M. Andrychowicz, J. Henriques, W. Kotlowski, G. Varol among others at amazing about deep generative modeling. Slides:

    Poništi
  18. proslijedio/la je Tweet

    We have a vacancy for an asst. prof. on Hybrid Intelligence: AI systems that collaborate with people instead of replacing them. We offer a top-100 Dept (Times Higher), a top-20 city (Mercer) and a fully funded PhD student to supervise (closes 6 Jan)

    Poništi
  19. proslijedio/la je Tweet
    25. stu 2019.

    JOB VACANCY: Interested in doing a Postdoc in Computational Statistics/Statistical Machine Learning in Oxford with me and Chris Holmes, please apply:

    Poništi
  20. proslijedio/la je Tweet
    22. stu 2019.

    . czy mogą wysyłać w świat przekaz, że jest już superzaawansowana. Znawcy tematu widzą jednak, jak bardzo te wszystkie algorytmy są jeszcze ograniczone - o trendach w badaniach mówi

    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:

    ·