Nurma

[Nurma @NurmaMSU]

@heysaik 🤣

[Nurma @NurmaMSU]

@jeffclune ai-authored article?

[Nurma @NurmaMSU]

@higgsfield_ai Wow!

[Nurma @NurmaMSU]

@Tim_Qian Cool!

[Nurma @NurmaMSU]

@NVIDIAAIDev brick

[Nurma @NurmaMSU]

Do you remember when you joined X? I do! #MyXAnniversary

[Nurma @NurmaMSU]

@pulkitology In 2022 we did exactly the same experiment with humanoid: BC + residual RL
https://t.co/VU7Y26ACMf

[Nurma @NurmaMSU]

@higgsfield_ai @nebiusofficial Nice!

[Nurma @NurmaMSU]

@xf1280 I'm fascinated by your research. Would it be possible for you to share the simulation environment for dexterous manipulator robot? I believe it would significantly benefit my research.

[Nurma @NurmaMSU]

@_akhaliq Mind blowing

[Nurma @NurmaMSU]

@robo_challenge I prepared some solutions, but couldn't find how to submit it. Can you please help with this?

[Nurma @NurmaMSU]

@facebookai Does it work with batch of images?

[Nurma @NurmaMSU]

Вы помните, когда зарегистрировались в Твиттере? Я помню! #МояГодовщинаВТвиттере

[Nurma @NurmaMSU]

@ARGleave @iclr_conf Until now I did not believe in contactless fight. But now you have changed my mind😂 Some funny fights https://t.co/pqisL3sk6k

[Google DeepMind @GoogleDeepMind]

Deep RL agents are data hungry and often learn task-specific representations. Our model learns object-centric abstractions from raw videos. This enables highly data-efficient RL and structured exploration. https://t.co/AnYkOYKRTO

[Two Minute Papers @twominutepapers]

.@Kaplanyan has been killing it with these foveated reconstruction papers. Absolutely amazing that this is possible with so little data. Have a look! - https://t.co/pl7nHbDpkn

[Reza Zadeh @Reza_Zadeh]

Dataset: 64 minutes of challenging pedestrian areas captured with:
- stereo cylindrical 360 RGB cam
- 3D point clouds from two Veloydyne 16 Lidars
- line 3Dpoint clouds from two Sick Lidars
- Audio, RGBD, 360 spherical image from a fisheye camera

https://t.co/5zYzwwpRBM

[AI at Meta @AIatMeta]

We’ve developed one of the first systems that uses only 3D point clouds and achieves higher precision in detecting 3D objects than prior work. Read more: https://t.co/64RCwWsrcN. And we’ve open-sourced this model here: https://t.co/fJl0hXR5nq #ICCV2019

[AK @_akhaliq]

Celeb-DF: A New Dataset for DeepFake Forensics
pdf: https://t.co/XvxOJCOqR2
abs: https://t.co/n7rRyDnYV7
github: https://t.co/ZWXieLTRuW