Add library_name, license, improve description, and add model weights link
Browse filesThis PR improves the model card by:
- Adding the `library_name: pytorch` to the metadata.
- Including a more detailed model description based on the paper abstract.
- Adding a link to the trained model weights on Hugging Face.
- Requesting clarification on the correct license. Please update the `license` field in the metadata accordingly.
README.md
CHANGED
|
@@ -6,11 +6,25 @@ tags:
|
|
| 6 |
- learning
|
| 7 |
- world
|
| 8 |
- models
|
|
|
|
|
|
|
| 9 |
---
|
|
|
|
| 10 |
# M<sup>3</sup>: A Modular World Model over Streams of Tokens
|
| 11 |
-
📄 [Paper](https://arxiv.org/abs/2502.11537) ▪️ 💾 [Code](https://github.com/leor-c/M3)
|
| 12 |
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
|
|
|
| 16 |
|
|
|
|
|
|
|
|
|
| 6 |
- learning
|
| 7 |
- world
|
| 8 |
- models
|
| 9 |
+
library_name: pytorch
|
| 10 |
+
license: other
|
| 11 |
---
|
| 12 |
+
|
| 13 |
# M<sup>3</sup>: A Modular World Model over Streams of Tokens
|
|
|
|
| 14 |
|
| 15 |
+
📄 [Paper](https://arxiv.org/abs/2502.11537) ▪️ 💾 [Code](https://github.com/leor-c/M3) ▪️ 🧠 [Trained Model Weights](https://huggingface.co/leorc/M3)
|
| 16 |
+
|
| 17 |
+
M<sup>3</sup> is a modular world model that extends the token-based world model framework to handle diverse observation and action modalities through independent, modality-specific components. It incorporates improvements from existing literature to enhance agent performance and achieves state-of-the-art sample efficiency for planning-free world models. It is the first method of this kind to reach a human-level median score on Atari 100K, exhibiting superhuman performance on 13 games. The model weights provided here cover Atari 100K, DeepMind Control Suite Proprioceptive 500K, and Craftax (Symbolic) 1M.
|
| 18 |
|
| 19 |
+
<div align="center">
|
| 20 |
+
<img src="https://github.com/user-attachments/assets/14734453-38dd-4bc0-a2e0-349e4eec37a2" height="220" />
|
| 21 |
+
<img src="https://github.com/user-attachments/assets/11beac5f-f8ee-48a7-94ec-2130087ed060" height="220" />
|
| 22 |
+
<img src="https://github.com/user-attachments/assets/a7e89c77-754f-43e3-982c-423c1257846c" height="220" />
|
| 23 |
+
<img src="https://github.com/user-attachments/assets/2ae2791a-9aec-4649-88ad-56e9840cd6b1" height="220" />
|
| 24 |
+
<img src="https://github.com/user-attachments/assets/2d5f9c98-2468-4206-95ac-e4d370798d7e" height="220" />
|
| 25 |
+
</div>
|
| 26 |
|
| 27 |
+
<div align="center">
|
| 28 |
|
| 29 |
+
<img src="https://github.com/user-attachments/assets/32f547d1-198c-4cf4-8f4e-9f683250399a" height="350" />
|
| 30 |
+
</div>
|