PowerInfer/SmallThinker-3B-Preview
Text Generation
•
Updated
•
51.7k
•
353
program or die
programORdie2
·
AI & ML interests
None yet
Recent Activity
liked
a model
15 days ago
PowerInfer/SmallThinker-3B-Preview
liked
a dataset
3 months ago
SkunkworksAI/reasoning-0.01
liked
a model
3 months ago
KingNish/Reasoning-Llama-3b-v0.1
Organizations
None yet
programORdie2's activity
liked
a
model
15 days ago
liked
a
dataset
3 months ago
liked
3
models
3 months ago
liked
a
Space
3 months ago
liked
a
model
3 months ago
liked
a
Space
8 months ago
reacted to
vladbogo's
post with 👍
11 months ago
Post
Genie is a new method from Google DeepMind that generates interactive, action-controllable virtual worlds from unlabelled internet videos using.
Keypoints:
* Genie leverages a spatiotemporal video tokenizer, an autoregressive dynamics model, and a latent action model to generate controllable video environments.
* The model is trained on video data alone, without requiring action labels, using unsupervised learning to infer latent actions between frames.
* The method restricts the size of the action vocabulary to 8 to ensure that the number of possible latent actions remains small.
* The dataset used for training is generated by filtering publicly available internet videos with specific criteria related to 2D platformer games for a total of 6.8M videos used for training.
Paper: Genie: Generative Interactive Environments (2402.15391)
Project page: https://sites.google.com/view/genie-2024/
More detailed overview in my blog: https://huggingface.co/blog/vladbogo/genie-generative-interactive-environments
Congrats to the authors for their work!
Keypoints:
* Genie leverages a spatiotemporal video tokenizer, an autoregressive dynamics model, and a latent action model to generate controllable video environments.
* The model is trained on video data alone, without requiring action labels, using unsupervised learning to infer latent actions between frames.
* The method restricts the size of the action vocabulary to 8 to ensure that the number of possible latent actions remains small.
* The dataset used for training is generated by filtering publicly available internet videos with specific criteria related to 2D platformer games for a total of 6.8M videos used for training.
Paper: Genie: Generative Interactive Environments (2402.15391)
Project page: https://sites.google.com/view/genie-2024/
More detailed overview in my blog: https://huggingface.co/blog/vladbogo/genie-generative-interactive-environments
Congrats to the authors for their work!
- 3 replies
UNPAUSE
2
#345 opened about 1 year ago
by
programORdie2
ERROR while creating with API.
#175 opened over 1 year ago
by
programORdie2
liked
2
Spaces
over 1 year ago
API error
7
#19 opened over 1 year ago
by
programORdie2
Can't download from API
2
#3 opened over 1 year ago
by
programORdie2
updated
a
Space
over 1 year ago