Liu-Junhua/TwiFF-2.7M

---
license: apache-2.0
task_categories:
- any-to-any
- visual-question-answering
- image-text-to-text
language:
- en
tags:
- multimodal
- visual-chain-of-thought
- chain-of-thought
- visual-reasoning
size_categories:
- 1M<n<10M
---
# TwiFF (Think With Future Frames): A Large-Scale Dataset for Dynamic Visual Reasoning
<p align="center">
<a href="https://arxiv.org/abs/2602.10675">
<img
src="https://img.shields.io/badge/TwiFF-Paper-red?logo=arxiv&logoColor=red"
alt="TwiFF Paper on arXiv"
/>
</a>
<a href="https://huggingface.co/Liu-Junhua/TwiFF-7B">
<img
src="https://img.shields.io/badge/TwiFF-Model-yellow?logo=huggingface&logoColor=yellow"
alt="TwiFF Model"
/>
</a>
<a href="https://huggingface.co/datasets/Liu-Junhua/TwiFF-Bench">
<img
src="https://img.shields.io/badge/TwiFF--Bench-Dataset-yellow?logo=huggingface&logoColor=yellow"
alt="TwiFF-Bench Dataset"
/>
</a>
<a href="https://github.com/LiuJunhua02/TwiFF">
<img
src="https://img.shields.io/badge/TwiFF-Codebase-536af5?color=536af5&logo=github"
alt="TwiFF-Bench Dataset"
/>
</a>
</p>

## 🧠 Method

<p align="center"><img src="https://github.com/LiuJunhua02/TwiFF/raw/main/assets/data_show.png" width="95%"></p>
We present TwiFF, a unified model fine-tuned on a high-quality dynamic visual Chain-of-Thought (VCoT) dataset comprising 2.7 million samples. In dynamic multimodal question-answering tasks involving instructional, predictive, and camera, TwiFF iteratively generates future event frames alongside textual reasoning, thereby producing temporally coherent visual reasoning trajectories. Experimental results demonstrate that, on dynamic scenario reasoning benchmarks, our dynamic VCoT approach outperforms both static VCoT methods based on tool-calling paradigms and purely textual chain-of-thought baselines.

## ✍️ Citation

```bibtex
@article{liu2026twiff,
title={TwiFF (Think With Future Frames): A Large-Scale Dataset for Dynamic Visual Reasoning},
author={Liu, Junhua and Wang, Zhangcheng and Han, Zhike and Wang, Ningli and Liang, Guotao and Kuang, Kun},
journal={arXiv preprint arXiv:2602.10675},
year={2026},
}
```