Yoav Artzi

@yoavartzi

Assistant professor of Computer Science /🚡/ and . Situated language understanding, , ML

Vrijeme pridruživanja: lipanj 2011.

Tweetovi

Blokirali ste korisnika/cu @yoavartzi

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

  1. Prikvačeni tweet
    30. pro 2019.

    Looking to hire a developer/intern in the NYC area. Here is a quick (approximate) description. Please apply here: DM (or email) me with any questions. Please RT to spread the word! 🙏

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    30. sij

    The TACL submission deadline will be extended by 24 hours for the February cycle, due to some system downtime over a few hours right at the deadline on Saturday night. Apologies for any inconvenience.

    Poništi
  3. 29. sij

    Congratulations to for the 2020 Facebook PhD fellowship! And congrats to for receiving one as well. Good year for !

    Poništi
  4. proslijedio/la je Tweet
    28. sij
    Poništi
  5. 15. sij

    . is recruiting for his team in Austin -- looking for an amazing research position? Don't miss this opportunity!

    Prikaži ovu nit
    Poništi
  6. 15. sij

    Touchdown is now much easier to access! This is all because of the hard work and persistence of 's team in , including and Eugene Ie, and . This shows an amazing level of support and commitment to open research 👏👏👏 Thank you!

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    15. sij

    The CFP for EMNLP2020 is out! Note: the submission deadline was moved to May 11th, to avoid the clash with ICML notifications. Anonymity period starts on April 11th.

    Poništi
  8. 13. sij

    . CFP seems to be up, deadline May 8:

    Poništi
  9. proslijedio/la je Tweet
    11. sij

    Here's a thread surveying some 'classic' work on . Lots of people seem to be discussing this right now, but with partial references to the whole story. My aim is to highlight some of the philosophical and psychological issues in the history of the concept. 1/

    Prikaži ovu nit
    Poništi
  10. 30. pro 2019.

    To clarify: this is a full-time position.

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

    My research group (located at Cornell Tech campus in NYC) is looking to recruit a postdoc to work on topics related to causal inference, fairness in ML, and sequential decision making (bandits+RL). Positions are renewable (1-2 years). Please retweet to spread the word. 🙏

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

    My group is looking for PhD students this year. We're researching text generation, struct. prediction, generative NLP / vis, and compression. Also excited to hear what interests you. I'm at Cornell Tech in NYC (student's view below). If you are interested, apply to Cornell CS.

    Poništi
  13. 10. pro 2019.
    Poništi
  14. 5. pro 2019.

    This makes texsync work again in Overleaf.... game changer!

    Poništi
  15. proslijedio/la je Tweet
    4. pro 2019.

    Dear NLP, \aclfinalcopy % Uncomment this line to make Overleaf work 🤯💪🧙‍♀️

    Poništi
  16. proslijedio/la je Tweet

    Want to see how downstream results are affected by LSTM LM training configurations? Save time/compute: use 125 pretrained LSTM LMs from my recent EMNLP 2019 paper with : (Thanks to the people who pointed us to Zenodo)

    Poništi
  17. 25. stu 2019.

    Here is a short video about the work: All done by Valts Blukis (co-advised by myself and Ross Knepper), with help from Yannick Terme and Eyvind Niklasson All this thanks to the wonderful support of from and Wendy Schmidt

    Prikaži ovu nit
    Poništi
  18. 25. stu 2019.

    We evaluate with human evaluation because it’s the only known way to really account for the instruction semantics. This Gantt visualization is the best way we found to visualize Likert scores :)

    Prikaži ovu nit
    Poništi
  19. 25. stu 2019.

    We use an adversarial discriminator to be invariant to the type of observations (real vs. sim), and combine supervised learning (for the limited language data) and RL (for control dynamics) in a new async algorithm called SuReAL

    Prikaži ovu nit
    Poništi
  20. 25. stu 2019.

    We train *jointly* in simulation and the real world, so there’s no adaptation process. Oh, and *no* autonomous flight with the real drone during learning!

    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:

    ·