| --- |
| license: cc-by-nc-4.0 |
| pipeline_tag: image-text-to-text |
| --- |
| |
| # IVT-LR |
|
|
| ## Overview |
|
|
| This model was presented in the paper [Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space](https://huggingface.co/papers/2510.12603). |
|
|
| Interleaved Vision-Text Latent Reasoning (IVT-LR) is the first VLM framework that unifies textual and visual representations in the latent space and implements multimodal latent reasoning. Specifically, IVT-LR represents each reasoning step by combining two implicit parts: **latent text** and **latent vision**. We further introduce a progressive multi-stage training strategy to enable MLLMs to perform the above multimodal latent reasoning steps. |
|
|
| --- |
|
|
| ## Usage |
|
|
| This repository provides pretrained models for **Qwen2-VL on M3CoT** and **Chameleon on ScienceQA**. |
|
|
| To see detailed usage, including inference code and scripts for training, please refer to the [GitHub repository](https://github.com/FYYDCC/IVT-LR). |
|
|
| --- |
|
|
| ### Download Models |
|
|
| You can download the models directly from Hugging Face using `huggingface_hub`: |
|
|
| ```python |
| from huggingface_hub import hf_hub_download |
| |
| # Example: download Qwen2-VL model |
| qwen_model_path = hf_hub_download("FYYDCC/IVTLR", "qwen_vl/model.pth") |
| |
| # Example: download Chameleon model |
| chameleon_model_path = hf_hub_download("FYYDCC/IVTLR", "chameleon/model.pth") |
| ``` |
