Improve ReMind model discoverability
Browse files
README.md
CHANGED
|
@@ -3,19 +3,31 @@ license: cc-by-nc-4.0
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: image-to-video
|
|
|
|
|
|
|
| 6 |
base_model: Wan-AI/Wan2.2-TI2V-5B
|
| 7 |
base_model_relation: finetune
|
| 8 |
tags:
|
|
|
|
|
|
|
| 9 |
- video-generation
|
| 10 |
- image-to-video
|
| 11 |
- world-model
|
|
|
|
| 12 |
- causal-video-generation
|
|
|
|
|
|
|
|
|
|
| 13 |
- wan2.2
|
| 14 |
- lora
|
| 15 |
- arxiv:2605.25333
|
| 16 |
---
|
| 17 |
|
| 18 |
-
# ReMind 5B
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
ReMind post-trains a causal video generator to preserve and evolve hidden
|
| 21 |
world state through camera motion, occlusion, and illumination changes.
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: image-to-video
|
| 6 |
+
library_name: wan2.2
|
| 7 |
+
model_name: "ReMind 5B — Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution"
|
| 8 |
base_model: Wan-AI/Wan2.2-TI2V-5B
|
| 9 |
base_model_relation: finetune
|
| 10 |
tags:
|
| 11 |
+
- remind
|
| 12 |
+
- remind-5b
|
| 13 |
- video-generation
|
| 14 |
- image-to-video
|
| 15 |
- world-model
|
| 16 |
+
- video-world-model
|
| 17 |
- causal-video-generation
|
| 18 |
+
- dynamic-memory
|
| 19 |
+
- out-of-sight-state-evolution
|
| 20 |
+
- teaching-video-generators-to-remember
|
| 21 |
- wan2.2
|
| 22 |
- lora
|
| 23 |
- arxiv:2605.25333
|
| 24 |
---
|
| 25 |
|
| 26 |
+
# ReMind 5B — Teaching Video Generators to Remember
|
| 27 |
+
|
| 28 |
+
Official ReMind 5B checkpoints for **Teaching Video Generators to Remember:
|
| 29 |
+
Eliciting Dynamic Memory for Out-of-Sight State Evolution**
|
| 30 |
+
([arXiv:2605.25333](https://arxiv.org/abs/2605.25333)).
|
| 31 |
|
| 32 |
ReMind post-trains a causal video generator to preserve and evolve hidden
|
| 33 |
world state through camera motion, occlusion, and illumination changes.
|