Add transformers library tag and model description
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,13 +1,17 @@
|
|
| 1 |
---
|
| 2 |
pipeline_tag: video-text-to-text
|
|
|
|
| 3 |
---
|
|
|
|
| 4 |
# EVA: Efficient Reinforcement Learning for End-to-End Video Agent
|
| 5 |
|
| 6 |
[](https://arxiv.org/abs/2603.22918)
|
| 7 |
[](https://github.com/wangruohui/EfficientVideoAgent)
|
| 8 |
[](https://huggingface.co/WRHC/EfficientVideoAgent/)
|
| 9 |
|
| 10 |
-
This repository contains the official evaluation code for the model proposed in
|
|
|
|
|
|
|
| 11 |
|
| 12 |
|
| 13 |
|
|
|
|
| 1 |
---
|
| 2 |
pipeline_tag: video-text-to-text
|
| 3 |
+
library_name: transformers
|
| 4 |
---
|
| 5 |
+
|
| 6 |
# EVA: Efficient Reinforcement Learning for End-to-End Video Agent
|
| 7 |
|
| 8 |
[](https://arxiv.org/abs/2603.22918)
|
| 9 |
[](https://github.com/wangruohui/EfficientVideoAgent)
|
| 10 |
[](https://huggingface.co/WRHC/EfficientVideoAgent/)
|
| 11 |
|
| 12 |
+
This repository contains the official evaluation code for the model proposed in the paper [EVA: Efficient Reinforcement Learning for End-to-End Video Agent](https://arxiv.org/abs/2603.22918).
|
| 13 |
+
|
| 14 |
+
EVA (Efficient Video Agent) is an end-to-end framework that enables "planning-before-perception" through iterative summary-plan-action-reflection reasoning. Unlike passive recognizers, EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding.
|
| 15 |
|
| 16 |
|
| 17 |
|