Thomas Wolf

@Thom_Wolf

Science Lead @ HuggingFace🤗 Prev. PhD in physics @ UPMC - Pat. Attorney - & - Dad - Used to Build Magic Sandboxes

যোগদান করেছেন ফেব্রুয়ারী ২০১১

মিডিয়া

  1. ৮ জুন

    NeuralCoref v3.0 is out✨! - up to 100x faster than v2.0 (thanks Cython) 🚀 - Integrated in spaCy models and pipeline 🤗 + 💫 = 💙 - Based on the fast neural net model by , trained in Check it out: Cc

  2. ১৪ মে

    Lot of great works on Word/Sentence Embeddings in 2017/early-2018! ELMo by at , InferSent by et al., learning by multi-tasking from MILA/... and I wrote a post summarizing the current baselines, SOTA and trends

  3. ২২ এপ্রিল

    "Proof by intimidation" are way too common nowadays! But my favorites are proofs by "circular arguments"

  4. ১১ এপ্রিল

    You can tune the acceptance probability threshold T to trade-off computation for statistical accuracy

    এই থ্রেডটি দেখান
  5. ১১ এপ্রিল

    Interesting combination of variational inference and rejection sampling by & . Rejection sampling is not dead! And a nice blog post

    এই থ্রেডটি দেখান
  6. ১০ এপ্রিল

    The "Virtual Stunman" of @jasonpeng0, Sergey Levine and is a really nice piece of reinforcement learning combined with imitation learning. Interesting insights! And the blog post is great, check it out!

  7. ৬ এপ্রিল

    We take our neural nets too seriously. I see them more like this than any terminator-like robot.

  8. ৫ এপ্রিল

    Neural net training in one slide. If you sometimes need to explain it to a general audience.

    এই থ্রেডটি দেখান
  9. ৪ এপ্রিল

    To introduce the work we'll be presenting at ICLR, I tried to draft the most visual & intuitive introduction to Meta-Learning I could come up with. Check it out if you like watching cute animated neurons sending information and gradients to each other!

    এই থ্রেডটি দেখান
  10. ২৯ মার্চ

    story at is a nice one: reading a lot about theoretical physics as a kid he found out that even the greatest physicists struggled with problems like the great unification theory. Decided to switch to AI to build something that could augment humans

  11. ২৯ মার্চ

    and at on the problem of black box algorithmic newsfeeds/ads. Dreaming of a "why" button that'd tell you "I showed you this ad because you clicked on this earlier and a third-party told me you bought this from them"

    এই থ্রেডটি দেখান
  12. ২৯ মার্চ

    at on the huge importance of understanding failure cases and bias in the algorithms we use at large scale, not only in gov but also big private comp. Deeply resonate with the latest article of I read yesterday

  13. ২৯ মার্চ

    Justine Cassell from CMU on crafting human-compatible AI and how conversational AI could actually help improve human-human interactions (think of a positive/compassionate AI that gives you confidence in yourself / power to reconnect to others when you are down)

  14. ২৯ মার্চ

    Really proud of the way the French gov is embracing and questioning the AI revolution! At today in Paris with a crazy lineup, half a day of debats between Berkeley's Stuart Russell

  15. ২০ মার্চ

    Yeepee 🎉 Our first submited paper was accepted (workshop track)! More about it soon!

  16. ২০ মার্চ

    What is more interesting that a SOTA Deep Learning model? A good paper studying the limits of a SOTA model!

    এই থ্রেডটি দেখান
  17. ২৬ সেপ্টেম্বর, ২০১৭
  18. ৭ সেপ্টেম্বর, ২০১৭

    Improving latent variable models for dialog generation by Julian Serban, A. Ororbia et al. Super interesting !

  19. ৭ সেপ্টেম্বর, ২০১৭

    Great talk by on going down to character (bytes ?) level in NMT at . Philosophical questions inside !

লোড হতে বেশ কিছুক্ষণ সময় নিচ্ছে।

টুইটার তার ক্ষমতার বাইরে চলে গেছে বা কোনো সাময়িক সমস্যার সম্মুখীন হয়েছে আবার চেষ্টা করুন বা আরও তথ্যের জন্য টুইটারের স্থিতি দেখুন।

    আপনিও পছন্দ করতে পারেন

    ·