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:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CewEhao/VideoSEAL_8B") model = AutoModelForCausalLM.from_pretrained("CewEhao/VideoSEAL_8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add paper link and citation
Verified signatureThis PR improves the model card by: - Linking the model to its official research paper: [VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority](https://huggingface.co/papers/2605.12571). - Adding a paper badge to the header for better visibility. - Adding a BibTeX citation section to facilitate proper attribution for researchers.07c952a
-
docs: add model card YAML metadata
8ca702c -
docs: align README with VideoSEAL (ICML 2026) — fix model link, paper subtitle, paths, conda env
987d21c -
Mirror of Echo23333456/VideoSEAL_8B
Verified signature14d11e9 -
initial commit
Verified signature0c75a5a