Sameer Singh

@sameer_

Assistant Prof at UC Irvine, working on machine learning and natural language processing ()

Vrijeme pridruživanja: ožujak 2009.

Tweetovi

Blokirali ste korisnika/cu @sameer_

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

  1. Prikvačeni tweet
    7. lis 2018.

    We've decided to start writing a blog with summaries of papers that we discuss in our reading group, thanks to a suggestion from (and a tweet by ). Look forward to tweets about summaries, or follow the blog.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    4. velj

    Just a reminder to everyone -- AKBC abstract deadline is only 2 days away! Please submit your papers to this new and exciting conference! (cc )

    Poništi
  3. proslijedio/la je Tweet
    4. velj

    SafeAI-20 is very pleased to announce the Invited Talk by Sameer Singh. (University of California). Evaluating and Testing Natural Language Processing Systems. Invited Speakers infoat:

    Poništi
  4. proslijedio/la je Tweet

    may be over, but the (newly renamed!) FAccT Network is here for you year-round! Our latest Network event: KG-BIAS 2020, Bias in Automatic Knowledge Graph Construction, at :

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    3. velj

    The workshop invited talks feature Ray Mooney, , , , , and Dan Roth. Details here: See you in New York!

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

    AKBC 2020 Abstract Deadline (February 6) is next week! Full papers are due Feb 13th! Please submit your finest work to the conference. Website () has been updated with submission details.

    Poništi
  7. proslijedio/la je Tweet

    Just noticed that there is an HBR article that discusses our recent work on fooling ML explanation methods: . Yayy! Our paper:

    Poništi
  8. proslijedio/la je Tweet
    31. sij

    An insightful conversation about AI Explainability from , , (moderated by )

    Poništi
  9. proslijedio/la je Tweet
    26. sij

    Protip: If your deep neural network won’t converge, try remodulating the shield frequencies and reconfiguring the plasma relay to emit a rapid EM burst directly at the subspace anomaly.

    Poništi
  10. proslijedio/la je Tweet
    23. sij

    It's been an incredible life journey that brought me across the world to become a researcher, and it looks like the best is still to come: I am excited to join a vibrant, innovative, thoughtful environment at as an Assistant Professor starting this summer!

    Poništi
  11. proslijedio/la je Tweet

    I have a favor to ask. For 20+ years I've been working on a dream: to make all science funded by US taxpayers freely available to all. We are on the verge of achieving this. But we need to show that people care. So please, if you can, sign this letter:

    Poništi
  12. proslijedio/la je Tweet
    19. sij
    Poništi
  13. proslijedio/la je Tweet
    16. sij

    AKBC 2020 Abstract Deadline (February 6) is less than a month away! Please submit your work to the conference. Website () has been updated with submission details.

    Poništi
  14. proslijedio/la je Tweet
    16. sij
    Poništi
  15. proslijedio/la je Tweet
    9. sij

    We ( Ananth, , , ) , are pleased to announce the release of ORB, an Open Reading Benchmark. This is an evaluation server that tests a single model on a variety of reading comprehension datasets (SQuAD, DROP, Quoref, ...).

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

    Introducing "Neural Module Networks for Reasoning over Text" accepted to ICLR 2020 w/ Kevin Lin (), Dan Roth (), Sameer Singh () and Matt Gardner (). Paper: Code: Coming soon! [1/4]

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    30. pro 2019.

    Can an AI model write weird-twitter tweets as well as a human? Let's find out! Try and distinguish tweets from and here: I got 4/10 on my first try.

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    19. pro 2019.
    Poništi
  19. proslijedio/la je Tweet
    13. pro 2019.

    At 4:45 I'm giving an invited talk at the KR2ML workshop Title: "Circuit Languages at the Confluence of and " Slides:

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

    Presenting some analysis of compositionality in pre-trained models for VQA (work w/ and ) today at the ViGIL Workshop. Giving a spotlight some time b/w 10:30 and 10:50 and will be at poster session from 12:10 to 1:50 pm. Please stop by and discuss!

    Poništi
  21. proslijedio/la je Tweet
    5. pro 2019.
    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:

    ·