The Stanford AI Lab

@StanfordAILab

The portal for members of the Stanford Artificial Intelligence Laboratory (SAIL) to share their latest news, research, and more! ⛵️🤖

Vrijeme pridruživanja: studeni 2018.

Tweetovi

Blokirali ste korisnika/cu @StanfordAILab

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

  1. proslijedio/la je Tweet

    To all at that have not heard through the grapevine yet: I am convening sessions called ‘Wonks and Techies’ for people interested in technology and policy. You are welcome to join! Email me at my address 🙏🏻

    Poništi
  2. proslijedio/la je Tweet
    31. sij

    Really excited to have hosted for the Stanford Robotics Lunch seminar. Pete not only shared **impressive** real world results but also lots of practical advice on how to train robust visuomotor policies. Thanks so much for swinging by Pete!

    Poništi
  3. proslijedio/la je Tweet
    29. sij

    And former ⁦⁩ PhD Student Angel Chang now at Simon Fraser is number 3 in this group of 10 ⁦⁩ videos on people in AI

    Poništi
  4. proslijedio/la je Tweet
    29. sij

    Here’s an article in ⁦⁩ about recent ⁦ postdoc and ⁦⁩ PhD student ⁦ touching on human language, , and deep learning

    Poništi
  5. 28. sij

    Congratulations to Michelle Guo () from ⁦⁩—and all the other wonderful winners—on receiving a 2020 Fellowship award

    Poništi
  6. proslijedio/la je Tweet
    27. sij

    We made the first place at the NuScenes Tracking Challenge (AI Driving Olympics ) Spoiler alert: It's a Kalman filter! We beat the AB3DMOT baseline by a large margin. arXiv

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

    Announcing Minkowski Engine version 0.4 with 3D sparse tensor reconstruction and better coordinate management, and documentation! Please check out

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

    Through 's summer program, students will work closely with a mentor on an original cognitive science research project. Learn more and apply by Feb. 1:

    Poništi
  9. proslijedio/la je Tweet
    23. sij

    We present Interactive Gibson Benchmark, a benchmark for interactive navigation in cluttered environments. We provide baselines with different trade-offs between navigation path efficiency and disturbance of surrounding objects. Code + paper:

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    23. sij

    Do not miss this! Hosted by Associate Director Prof. Russ Altman! Most of these top 5 interviews come from faculty affiliated with , including Associate Director and Prof. !

    Poništi
  11. proslijedio/la je Tweet
    23. sij

    Very excited by our research on perceptual robotics. members and collaborators will present 6 research papers at this year’s I’m starting to feel like a legit robotics researcher ;)

    Poništi
  12. proslijedio/la je Tweet
    22. sij

    Semantic annotations for the medium Gibson split are now available for download! We generated them with our automatic labeling pipeline presented in . Stay tuned for the labeling and 3D scene graph computation code. Download the data here:

    Poništi
  13. proslijedio/la je Tweet
    23. sij

    We have two papers on learning keypoint representations for robot manipulation accepted in . 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints KETO: Learning Keypoint Representations for Tool Manipulation

    Poništi
  14. proslijedio/la je Tweet
    22. sij

    Our paper with & "Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction" accepted for presentation ! Stanford-TRI Intent Prediction (STIP) dataset & the paper coming out soon! Stay tuned!

    Poništi
  15. proslijedio/la je Tweet
    22. sij
    Poništi
  16. proslijedio/la je Tweet
    22. sij

    Excited to share PCGrad, a super simple & effective method for multi-task learning & multi-task RL: project conflicting gradients On Meta-World MT50, PCGrad can solve *2x* more tasks than prior methods w/ Tianhe Yu, S Kumar, Gupta, ,

    Poništi
  17. proslijedio/la je Tweet
    21. sij

    I have post-doc openings in my lab. Do you want to use empirical methods, design experiments, and collaborate with both large and small tech firms for research and social impact? Have interest in ed tech, fin tech, charitable giving, and social sector effectiveness? Apply! 1/3

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

    It is now an ICRA 2020 paper!! More details to come.

    Poništi
  19. 22. sij
    Poništi
  20. proslijedio/la je Tweet
    20. sij

    We propose a method for in-hand manipulation that combines low-level manipulation primitives with a learned, mid-level policy that orchestrates these primitives. Our method keep the object firmly grasped while transporting it to distant goal poses.

    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:

    ·