Thành Lê

@The_UBD

Hà Nội, Việt Nam
Vrijeme pridruživanja: svibanj 2017.

Tweetovi

Blokirali ste korisnika/cu @The_UBD

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

  1. proslijedio/la je Tweet
    2. velj

    Got promoted to a full professor at CMU:) Thanks to my amazing students, collaborators, and my mentors. CMU is a remarkable place, but what makes it truly unique is its brilliant students! Hard to find a better place to do ML and AI.

    Poništi
  2. proslijedio/la je Tweet
    31. sij

    Today we announce a novel, open-source method for text generation tasks (e.g., summarization or sentence fusion), which uses edit operations instead of generating text from scratch, leading to less errors and faster model execution. Read about it below.

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    An Opinionated Guide to ML Research: “To make breakthroughs with idea-driven research, you need to develop an exceptionally deep understanding of your subject, and a perspective that diverges from the rest of the community—some can do it, but it’s hard.”

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

    Transformers 2.4.0 is out 🤗 - Training transformers from scratch is now supported - New models, including *FlauBERT*, Dutch BERT, *UmBERTo* - Revamped documentation - First multi-modal model, MMBT from , text & images Bye bye Python 2 🙃

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

    People asking me to teach classes clearly give zero fuck to the imposter syndrome of a former physics PhD turned lawyer before joining AI Anyway I'll co-teach NLPL Winter School w Yoav Goldberg talking transfer learning, its limits & where the field might head Will share slides

    Poništi
  6. proslijedio/la je Tweet
    28. sij

    Introducing the new Thinc, a refreshing functional take on deep learning! 🔮 Static type checking 🔥 Mix , & ⛓️ Integrated config system 🧮 Extensible backends incl. JAX (experimental) 🧬 Variable-length sequences & more

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

    Introducing , a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness! Paper: Sample conversations:

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    24. sij

    Facebook's AI Residency program, which gives residents 12 months of practical experience in AI working with leading researchers, is accepting applications until January 31st! Current residents Diana and Eric discuss their experience in this Q&A:

    Poništi
  9. proslijedio/la je Tweet
    23. sij

    Today gave a talk at Google Research Berlin about our Transformer analysis work. Met a lot of great people and feel totally happy :) Want to know details? Here are the blog posts: The Story of Heads: , Evolution of Representations:

    Poništi
  10. proslijedio/la je Tweet
    24. sij

    We're releasing mBART, a new seq2seq multilingual pretraining system for machine translation across 25 languages. It gives significant improvements for document-level translation and low-resource languages. Read our paper to learn more:

    Poništi
  11. proslijedio/la je Tweet
    23. sij

    Following the tradition, I am going to share all the course material for "STAT 453: Introduction to Deep Learning and Generative Models" I am teaching this semester :)

    Poništi
  12. proslijedio/la je Tweet
    21. sij

    🚨New lecture series🚨 We've teamed up with to bring you the Deep Learning Lecture Series: 12 lectures covering a range of topics in Deep Learning - all led by DeepMind researchers, all free, and all open to everyone. Info & tickets:

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    17. sij

    To make my research more reproducible, extensible and comparable to that of others & out of need to homogenize the language we use to express nn pruning methods, I contributed `nn.utils.prune` to 1.4 (see highlights ) Try it out & build on it! 🔥

    Poništi
  14. proslijedio/la je Tweet
    18. sij

    Open Syllabus Project Open Syllabus is a non-profit organization that maps the curriculum of higher education. Database of / stats from 7M class syllabi 👏

    Poništi
  15. proslijedio/la je Tweet
    14. sij

    BigGAN samples are famously photo-realistic but limited in diversity for some classes. Slightly modifying only the class embeddings (network unchanged) can reduce the diversity gap by ~50%! Work with Long Mai and led by fantastic !! Paper & video:

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

    By restructuring math expressions as a language, Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems.

    Poništi
  17. proslijedio/la je Tweet
    14. sij

    Great advice from on why you should release your code and make it as easy to use! It usually takes me >4 days to prepare the code, though. Getting it readable, well-explained, clean and logical (yet still equivalent to the original experiments) usually takes 1-2 weeks

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    14. sij

    I often meet research scientists interested in open-sourcing their code/research and asking for advice. Here is a thread for you. First: why should you open-source models along with your paper? Because science is a virtuous circle of knowledge sharing not a zero-sum competition

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

    2.1 is out 👍 Notable features: - The experimental TextVectorization layer allows you to include your text processing logic inside your model (for cleaner deployment & serialization) - The standard TF pip package now includes GPU support by default

    Poništi
  20. proslijedio/la je Tweet
    7. sij

    . people’s papers #2—ELECTRA: and colleagues (incl. at ) show how to build a much more compute/energy efficient discriminative pre-trainer for text encoding than BERT etc. using instead replaced token detection

    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:

    ·