Model card: paper, code, citation
Browse files
README.md
CHANGED
|
@@ -12,7 +12,11 @@ tags:
|
|
| 12 |
|
| 13 |
Checkpoint bundles for **FAR**, a latent-diffusion world model with a learned,
|
| 14 |
action-conditioned retrieval memory, and its baselines, on the LoopNav,
|
| 15 |
-
SoundSpaces and AI2-THOR corpora.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Layout
|
| 18 |
|
|
@@ -80,4 +84,12 @@ see the code repository's THIRD_PARTY_NOTICES.md.
|
|
| 80 |
|
| 81 |
## Citation
|
| 82 |
|
| 83 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
Checkpoint bundles for **FAR**, a latent-diffusion world model with a learned,
|
| 14 |
action-conditioned retrieval memory, and its baselines, on the LoopNav,
|
| 15 |
+
SoundSpaces and AI2-THOR corpora.
|
| 16 |
+
|
| 17 |
+
- Paper: [Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models](https://arxiv.org/abs/2609.34677)
|
| 18 |
+
- Code: https://github.com/sony/far
|
| 19 |
+
- Project page: https://1202kbs.github.io/FAR-Project-Page/
|
| 20 |
|
| 21 |
## Layout
|
| 22 |
|
|
|
|
| 84 |
|
| 85 |
## Citation
|
| 86 |
|
| 87 |
+
```bibtex
|
| 88 |
+
@article{kim2026far,
|
| 89 |
+
title = {Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models},
|
| 90 |
+
author = {Kim, Beomsu and Lai, Chieh-Hsin and Nguyen, Bac and Bar, Amir and Ye, Jong Chul and Mitsufuji, Yuki},
|
| 91 |
+
journal = {arXiv preprint arXiv:2609.34677},
|
| 92 |
+
year = {2026},
|
| 93 |
+
url = {https://arxiv.org/abs/2609.34677}
|
| 94 |
+
}
|
| 95 |
+
```
|