Video-Text-to-Text
Transformers
Safetensors
English
qwen3
text-generation
video-understanding
long-video-understanding
agentic-llm
video-question-answering
vision-language-model
grpo
reinforcement-learning
icml-2026
text-generation-inference
Instructions to use CewEhao/VideoSEAL_8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CewEhao/VideoSEAL_8B with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CewEhao/VideoSEAL_8B") model = AutoModelForCausalLM.from_pretrained("CewEhao/VideoSEAL_8B") - Notebooks
- Google Colab
- Kaggle
docs: add model card YAML metadata
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
<h2 align="center">🎬 VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority</h2>
|
| 2 |
|
| 3 |
<p align="center">
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: video-text-to-text
|
| 5 |
+
base_model: Qwen/Qwen3-8B
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- video-understanding
|
| 10 |
+
- long-video-understanding
|
| 11 |
+
- agentic-llm
|
| 12 |
+
- video-question-answering
|
| 13 |
+
- vision-language-model
|
| 14 |
+
- grpo
|
| 15 |
+
- reinforcement-learning
|
| 16 |
+
- icml-2026
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
<h2 align="center">🎬 VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority</h2>
|
| 20 |
|
| 21 |
<p align="center">
|