Hugging Face's logo

WRHC
/
EfficientVideoAgent

Video-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
text-generation-inference
Model card Files
xet
 Community
1
WRHC commited on
Commit
d311e03
·
1 Parent(s): 554d88f

update readme

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -5,11 +5,12 @@ library_name: transformers
5
 
6
  # EVA: Efficient Reinforcement Learning for End-to-End Video Agent
7
 
8
- [![Paper](https://img.shields.io/badge/Paper-Link-b31b1b.svg)](https://arxiv.org/abs/2603.22918)
9
- [![GitHub](https://img.shields.io/badge/GitHub-Repository-black.svg)](https://github.com/wangruohui/EfficientVideoAgent)
10
- [![Model](https://img.shields.io/badge/Model-Link-blue.svg)](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
 
 
5
 
6
  # EVA: Efficient Reinforcement Learning for End-to-End Video Agent
7
 
8
+ [![Paper](https://img.shields.io/badge/Paper-2603.22918-b31b1b.svg)](https://arxiv.org/abs/2603.22918)
9
+ [![Paper](https://img.shields.io/badge/Paper-2603.22918-yellow.svg)](https://huggingface.co/papers/2603.22918)
10
+ [![GitHub](https://img.shields.io/badge/GitHub-EfficientVideoAgent-black.svg)](https://github.com/wangruohui/EfficientVideoAgent)
11
+ [![Model](https://img.shields.io/badge/Model-EfficientVideoAgent-blue.svg)](https://huggingface.co/WRHC/EfficientVideoAgent/)
12
 
13
+ This repository contains the model weights proposed in our paper [EVA: Efficient Reinforcement Learning for End-to-End Video Agent](https://arxiv.org/abs/2603.22918). Official evaluation codes are hosted on [GitHub](https://github.com/wangruohui/EfficientVideoAgent).
14
 
15
  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.
16