Qiming (Bill) Bao

@qiming_bao

Ph.D. Candidate in ; R&D Engineer LAIR, AIIT, ; AI, NLP, DL; ex: (First-class Honours), , Orion Health.

Auckland, New Zealand
linkedin.com/in/bill-qiming…
Vrijeme pridruživanja: studeni 2019.
3 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @qiming_bao

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

  1. proslijedio/la je Tweet
    3. velj

    Break it down! Introducing the "Break" benchmark for testing the ability of models to break down a question into required steps for computing the answer. Accepted for . Learn more about Break in this post by Tomer Wolfson on the AI2 Blog:

    32 proslijeđena tweeta 104 korisnika označavaju da im se sviđa
    Poništi
  2. 27. sij

    Don't forget to practice at 4 am.

    The impact Kobe had on so many lives in so many ways... unimaginable heartbreak 💔
    1 korisnik označava da mu se sviđa
    Poništi
  3. proslijedio/la je Tweet
    22. sij

    I see many papers that begin with a sentence equivalent to "Topic X is popular". Popularity is not a sound scientific reason for studying a topic, so such opening sentences strike me as lame. How about "This paper shows how to solve issue Y with method M for X"? 1/2

    13 replies 54 proslijeđena tweeta 351 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    21. sij

    Do not apply over-sampling before splitting train and test

    Our paper "Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling" has been published on arXiv: What did we do? A thread... (1/6)
    Prikaži ovu nit
    1 reply 2 proslijeđena tweeta 16 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    18. pro 2018.

    What goes on in the mind of BERT? Using an interactive visualization tool, we uncovered some surprisingly intuitive patterns. Article: Colab: Github: Play with it and share what you find!

    8 replies 288 proslijeđenih tweetova 868 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    20. sij

    Terrific to see our workshop in graph neural networks (DLG'19 in KDD'19) to be highlighted from IBM Research in 2019! Our upcoming GNN workshop - DLGMA'20 in AAAI20: Welcome everyone to attend and share!

    IBM Research continued its long history of leadership in 2019. Learn more about our researchers' most notable AI papers and contributions.
    3 proslijeđena tweeta 3 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    10. sij

    I'd love to see a serious attempt to do imagenet using scaled Inductive logic programming - not because I think it'd be competitive, or even good, but because I think we'd learn a lot if it worked at all. (If you think you can succeed at this, consider applying for PhD with me)

    1 reply 2 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  8. 8. sij

    A great talk from Prof. WAYNE LUK who has shared an application of the back-propagation method to the compiler architecture design and a new interpretability of deep learning models.

    1 proslijeđeni tweet
    Poništi
  9. proslijedio/la je Tweet
    28. stu 2018.

    Wayne Luk’s team gets impressive improvements in performance and energy-efficiency when moving computation from CPUs to FPGAs – mjesto: 170 Queen's Gate

    1 proslijeđeni tweet 14 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    12. ruj 2019.

    What if Harry Potter had been a Vampire? Our @emnlp2019 paper, “Counterfactual Story Reasoning and Generation”, presents the TimeTravel dataset that tests causal reasoning capabilities over natural language narratives.1/2 Paper: from and

    37 proslijeđenih tweetova 115 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. 24. pro 2019.

    Merry Christmas!

    2 korisnika označavaju da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    28. lis 2019.

    Check out our new paper "On the Cross-lingual Transferability of Monolingual Representations" (w/ & ) We challenge common beliefs of why mBERT works by showing that a monolingual BERT can also be transferred to new languages

    99 proslijeđenih tweetova 309 korisnika označava da im se sviđa
    Poništi
  13. 23. pro 2019.

    I guess the reason why the UC browser has such a high download volume is that the software is pre-installed on the phone, but I have to say that this browser is very powerful in news recommendations.

    Facebook owns the 4 most downloaded apps of the decade. How concerned should we be? And should govs/regulators do something?? Answers on a postcard...
    2 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    15. pro 2019.

    Some of the keywords in paper titles that have seen the most change from NeurIPS 2018 to 2019. - meta-learning, kernel methods, reinforcement learning are 🔥 - more hardware-aware, more theory-driven - recurrent & convolutional get little love Full NeurIPS recap coming soon!

    5 replies 64 proslijeđena tweeta 371 korisnik označava da mu se sviđa
    Poništi
  15. proslijedio/la je Tweet
    24. stu 2019.

    I wrote an 8k word doc on machine learning systems design. This covers: 1. Project setup 2. Data pipeline 3. Training & debugging 4. Serving with case studies, resources, and 27 exercises. This is the 1st draft so feedback is much needed. Thank you!

    1.655 proslijeđenih tweetova 7.094 korisnika označavaju da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    18. pro 2019.

    It took me a while to recap bc some papers are complex. Key points: - Destructing black box: convergence, generalization, neural tangent kernel - New approaches: Bayesian & uncertainty, graph, convex optimization - Neuroscience & bio-inspired algos - ...

    14 replies 270 proslijeđenih tweetova 948 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    15. pro 2019.

    Just wrapped ! Notes here:

    9 replies 298 proslijeđenih tweetova 1.073 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    15. pro 2019.

    What if faking the cat's face? This could be A superinteresting tool for studying consciousness of animals.

    0:56
    for cats. Cats can’t trust what’s real anymore.
    1 reply 4 proslijeđena tweeta 12 korisnika označava da im se sviđa
    Poništi
  19. 20. pro 2019.

    A list of topic-centric public data sources organized by . The project has been stared at more than 36.8k.

    Poništi
  20. 20. pro 2019.

    Jiamou Liu's AI Group,

    2 korisnika označavaju da im se sviđa
    Poništi

@qiming_bao još nije objavio nijedan Tweet.

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:

    ·