IntReal
Collection
https://yushaohan.github.io/IntReal/ • 7 items • Updated • 1
How to use yushaohan/IntReal-U1-8B-MoT-SFT-RL with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yushaohan/IntReal-U1-8B-MoT-SFT-RL", trust_remote_code=True, device_map="auto")📄 Paper · 🌐 Project Page · 🤖 Models · 🤗 Dataset · 🏆 Leaderboard · 💻 Code · 🎬 Video
The U1-8B-MoT checkpoint fine-tuned on IntReal-100K for multimodal interleaved generation.
Use our U1 inference script. See the inference guide for environment setup and usage.
Evaluate the model with the IntReal Evaluation Suite.
@misc{yu2026intrealrealworlddatasetbenchmark,
title={IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation},
author={Shaohan Yu and Jie Qin and Wende Tan and Haiwen Diao and Limeng Qiao and Yueming Lyu and Chenyang Si},
year={2026},
eprint={2610.38425},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2610.38425},
}
Base model
sensenova/SenseNova-U1-8B-MoT-Interleaved