1. X
  2. Nicklas Hansen
Log inSign up
Nicklas Hansen
317 posts
Image
user avatar
Nicklas Hansen
@ncklashansen
Postdoc @CILVRatNYU. Prev: PhD @UCSanDiego, intern @nvidia, @MetaAI, @UCBerkeley, BS/MS @DTU_Compute. I like robots 🤖, plants 🪴, and they/them pronouns 🏳️‍🌈
San Diego, CA
nicklashansen.com
Joined August 2018
703
Following
2,623
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    Nicklas Hansen
    @ncklashansen
    Jun 26
    Super excited to share the last paper of my PhD: "Hallucination in World Models is Predictable and Preventable"✨ We train a 350M-param generative world model on a large dataset w/ 210 tasks and show that we can predict *when* hallucination happens and use that to fix it! 🧵1/n
    Image
    00:00
    55K
  • user avatar
    Nicklas Hansen
    @ncklashansen
    Oct 31, 2024
    TD-MPC2 just got ~5x faster! The update is available in a separate "speedups" branch at the moment and will be merged into main soon. Special thanks to @VincentMoens for his help with this!
    Image
    12K
  • user avatar
    Nicklas Hansen
    @ncklashansen
    Jul 24, 2024
    New fun benchmark for RL researchers to stress test their algorithms! We release code + human driver data for imitation, and benchmark TD-MPC2 in a multi-track setting 🏎️💨
    user avatar
    Xiaolong Wang
    @xiaolonw
    Jul 24, 2024
    Besides reading cool papers, my Twitter account is mostly used for catching up @F1 news. Very excited about @LandoNorris 's great performance recently. Now we combine Formula Racing to AI research: The following video shows we train a Reinforcement Learning policy to drive a
    Image
    00:00
    6.7K
  • user avatar
    Nicklas Hansen
    @ncklashansen
    Jul 4, 2024
    New work led by @imgeorgiev! We show that TD-MPC2 world models can be used as differentiable simulators in a multi-task setting, and it even beats an *actual* differentiable simulator. Super fun collaboration and the results are really promising!
    user avatar
    Ignat Georgiev
    @imgeorgiev
    Jul 4, 2024
    🔔New Paper - PWM: Policy Learning with Large World Models Joint work with @VarunGiridhar3 @ncklashansen @animesh_garg PWM is a multi-task RL method which solves 80 tasks across different embodiments in <10m per task using world models and first-order gradient optimization🧵
    Image
    00:00
    4.8K
  • user avatar
    Nicklas Hansen
    @ncklashansen
    Jun 20, 2024
    Stop by to learn more about our latest work on world models!
    user avatar
    Alexander Soare
    @asoare159
    Jun 20, 2024
    For our next #LeRobot Paper Discussion, @ncklashansen will present his first authored TD-MPC, and beyond. The event starts at 4:30 PM GMT on 26 June and will run for 1 hr. Join us then at meet.google.com/ige-xrww-yea 🤗
    1.7K
  • See @ncklashansen's full profile

    Sign up
    Log in

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement