Yuke Zhu

@yukez

Researcher | Assistant Professor (Starting Fall 2020) | CS PhD | I teach robots to learn and see 🤖 | Opinions are my own

Stanford, CA
ai.stanford.edu/~yukez
Vrijeme pridruživanja: kolovoz 2008.
10 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @yukez

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

  1. Prikvačeni tweet
    2. ruj 2019.

    Life update: I will be joining as an Assitant Professor in starting Fall 2020. I am thrilled to continue my research on robot learning and perception as a faculty and look forward to collaborating with the exceptional faculty, researchers, and students at UT.

    15 proslijeđenih tweetova 377 korisnika označava da im se sviđa
    Poništi
  2. 2. velj

    Brilliant performance art of hacking Google Maps illustrating why we should keep a critical eye on our reliance on technology and algorithmic governance in our daily lives

    99 smartphones are transported in a handcart to generate virtual traffic jam in Google Maps. Through this activity, it is possible to turn a green street red which has an impact in the physical world by navigating cars on another route!
    Prikaži ovu nit
    1 reply 5 proslijeđenih tweetova 47 korisnika označava da im se sviđa
    Poništi
  3. 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

    4 proslijeđena tweeta 41 korisnik označava da mu se sviđa
    Poništi
  4. proslijedio/la je Tweet
    13. sij

    : I see overwhelming discussion on the downsides of academia. I worry what this does to the hope & inspiration of grad students with ambitions to go into academia. Given that I think is the best job ever, my thoughts on life as an academic. A thread 👇🏽

    735 proslijeđenih tweetova 2.814 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. 8. pro 2019.

    Excited about coming back to Vancouver, the beautiful city where I attended college, for Looking forward to catching up with the latest research and hanging out with friends!

    1 reply 1 proslijeđeni tweet 60 korisnika označava da im se sviđa
    Poništi
  6. 22. stu 2019.

    Some of my proudest memories of my PhD are working with people from different countries and being advised by a stellar all-women thesis committee. I encourage students from diverse backgrounds to apply for my future lab where diversity and inclusion will be valued.

    23 proslijeđena tweeta 256 korisnika označava da im se sviđa
    Poništi
  7. 16. stu 2019.

    Sharing the slides of my talk "Learning Keypoint Representations for Robot Manipulation" presented at the Workshop on Learning Representations for Planning and Control Slides: Workshop:

    1 reply 19 proslijeđenih tweetova 86 korisnika označava da im se sviđa
    Poništi
  8. 16. stu 2019.

    Very insightful blog post by Vincent Vanhoucke. Many of the principles are also applicable to Ph.D. students and academics.

    An old article by now but is a good read for anyone interested in career as a Research Scientist, by my boss at Google Brain Vincent Vanhoucke: "You will spend a career working on things that don't work". I'd say research is painfully exciting.
    4 proslijeđena tweeta 33 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    8. stu 2019.

    Smart people have realized one of my former startup ideas: ... there might be challenges but I really think it has high potential! Might become the new robot programming job!

    1 reply 7 proslijeđenih tweetova 21 korisnik označava da mu se sviđa
    Poništi
  10. proslijedio/la je Tweet
    5. stu 2019.

    De-An Huang from presents our work on Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning. Talk is today 11:15am at L1-R2 Work with Paper:

    19 proslijeđenih tweetova 75 korisnika označava da im se sviđa
    Poništi
  11. 5. stu 2019.

    Ajay gave a great talk on our RoboTurk project , nominated for Best Paper on Cognitive Robotics. Large-scale real robot dataset through crowd teleportation! More information can be found at

    Korisnici , i
    1 reply 22 proslijeđena tweeta 85 korisnika označava da im se sviđa
    Poništi
  12. 1. stu 2019.

    At next week, I will be giving invited talks: 1. "Learning How-To Knowledge from the Web" at AnSWeR (Mon) 2. "Learning Keypoint Representations for Robot Manipulation" at LRPC (Fri) Come to learn about our recent work!

    16 proslijeđenih tweetova 62 korisnika označavaju da im se sviđa
    Poništi
  13. 29. lis 2019.

    Introducing our work on hierarchical planning

    0:52
    We introduce CAVIN to hierarchically generate plans in learned latent spaces. Our robot learns to strategically interact with multiple objects in different tasks. Webpage: Paper: w/
    Prikaži ovu nit
    6 proslijeđenih tweetova 27 korisnika označava da im se sviđa
    Poništi
  14. 29. lis 2019.

    KETO keeps tool representations slim and strong. We developed a self-supervised learning framework of KEpoint representations for TOol manipulation. Check it out!

    0:28
    What is a good representation for understanding tools? We introduce KeTo, a learned keypoint representation for tool use and tool creation. Webpage: Paper: Joint work w/ Zengyi, , ,
    1 reply 4 proslijeđena tweeta 16 korisnika označava da im se sviđa
    Poništi
  15. 28. lis 2019.

    I am super excited to attend in Osaka this week and in Macau next week, presenting our recent works on Hierarchical Planning and RoboTurk. Looking forward to catching up with friends and colleagues! Drop me a message if you'd like to have coffee and chat!

    5 proslijeđenih tweetova 46 korisnika označava da im se sviđa
    Poništi
  16. 24. lis 2019.

    Dear academics, check out our 6 pack!! 💪 Ok... I meant 6-PACK, our new 6DoF Pose Anchor-based Category-level Keypoint tracker, real-time tracking of novel objects without known 3D models!

    We present 6-PACK, an RGB-D category-level 6D pose tracker that generalizes between instances of classes based on a set of anchors and keypoints. No 3D models required! Code+Paper: w/ Chen Wang Jun Lv
    1 reply 38 proslijeđenih tweetova 199 korisnika označava da im se sviđa
    Poništi
  17. 21. lis 2019.

    ... and I could never complete these works without collaborating with a group of brilliant people - check out them in the last slide of the talk :)

    10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 21. lis 2019.

    Releasing my Stanford Ph.D. dissertation and talk slides "Closing the Perception-Action Loop: Towards Building General-Purpose Robot Autonomy", a summary of my work on robot perception and control Slides: Dissertation:

    63 proslijeđena tweeta 339 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 11. lis 2019.

    Awww Michelle, I am flattered by your kind words. And yes, we are hiring!

    Yuke is an amazing researcher, collaborator, and mentor. If you want to work on cutting edge research in the intersection of robotics, perception, and learning, consider working and applying to for grad school!
    11 korisnika označava da im se sviđa
    Poništi
  20. 9. lis 2019.

    Excited to start my gap year in ! Looking forward to a lot of new research opportunities with the brilliant minds!

    7 replies 6 proslijeđenih tweetova 205 korisnika označava da im se sviđa
    Poništi
  21. 6. lis 2019.

    New work: we built a meta-learning algorithm for an agent to discover the causal and effect relations from its visual observations and to use such causal knowledge to perform goal-directed tasks. Paper: Joint work w/

    Korisnici , i
    5 replies 110 proslijeđenih tweetova 495 korisnika označava da im se sviđa
    Poništi

@yukez 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:

    ·