---
license: mit
library_name: transformers
pipeline_tag: robotics
tags:
- embodied-ai
- reinforcement-learning
- multimodal-llm
- computer-vision
---

<h2 align="center">
  <b>Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration</b>

  <b><i> CVPR 2026</i></b>
</h2>

<p align="center">
    <a href="https://arxiv.org/abs/2601.10744">
    <img src="https://img.shields.io/badge/Paper-arXiv-B31B1B?style=flat-square&logo=arxiv&logoColor=red">
    </a>
    <a href="https://wangsen99.github.io/papers/lmee/">
    <img src="https://img.shields.io/badge/Project-Page-4285F4?style=flat-square&logo=google-chrome&logoColor=blue">
    </a>
    <a href="https://github.com/wangsen99/LMEE">
    <img src="https://img.shields.io/badge/Code-Github-black?style=flat-square&logo=github">
    </a>
</p>

## MemoryExplorer

**MemoryExplorer** is a multimodal large language model (MLLM) framework designed for Long-term Memory Embodied Exploration (LMEE). It unifies an agent's exploratory cognition and decision-making behaviors to promote lifelong learning in complex environments. 

The model is fine-tuned through reinforcement learning to encourage active memory querying using a multi-task reward function that includes action prediction, frontier selection, and memory-based question answering. 

### Resources
- **Paper:** [Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration](https://huggingface.co/papers/2601.10744)
- **Project Page:** [https://wangsen99.github.io/papers/lmee/](https://wangsen99.github.io/papers/lmee/)
- **Repository:** [https://github.com/wangsen99/LMEE](https://github.com/wangsen99/LMEE)
- **Benchmark:** [LMEE-Bench](https://huggingface.co/datasets/wangsen99/LMEE-Bench)

## Citation

If you find this work useful, please consider citing:

```bibtex
@inproceedings{wang2026explore,
  title={Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration},
  author={Wang, Sen and Liu, Bangwei and Gao, Zhenkun and Ma, Lizhuang and Wang, Xuhong and Xie, Yuan and Tan, Xin},
  booktitle={Proceedings of the IEEE/CVF Computer Vision and Pattern Recognition (CVPR)},
  year={2026}
}
```