Update README.md

README.md

@@ -1,5 +1,44 @@
 ---
 license: apache-2.0
+language:
+- en
+base_model:
+- liuhaotian/llava-v1.5-7b
 ---
 
-Please stay tuned. Coming soon.
+# TRIM
+
+## Introduction
+
+We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance. 
+Inspired by human attention patterns in Visual Question Answering (VQA) tasks, TRIM presents a fresh perspective on the selection and reduction of image tokens. 
+The TRIM method has been extensively tested across 12 datasets, and the results demonstrate a significant reduction in computational overhead while maintaining a consistent level of performance. 
+This research marks a critical stride in efficient MLLM development, promoting greater accessibility and sustainability of high-performing models.
+
+ <img src="./images/TRIM.png" width="600" alt="TRIM" align="center" />
+
+TRIM significantly streamlines the computational process, reducing the number of image tokens by approximately 79%, processing time by 67%, and memory usage by 30% relative to the baseline (LLaVA-1.5-7B).
+
+<img src="./images/fig1.png" width="300" alt="stat2"/>
+
+## How to use?
+
+Please refer to [Code for TRIM](https://github.com/FreedomIntelligence/TRIM?tab=readme-ov-file#run).
+
+## Links
+
+- **Repository:** [TRIM GitHub](https://github.com/FreedomIntelligence/TRIM)
+- **Paper:** [Arxiv](https://arxiv.org/abs/2409.10994)
+- **Point of Contact:** [Dingjie Song](mailto:dingjiesong.cs@gmail.com)
+
+## Citation
+
+If you find this project useful in your research, please consider citing:
+```BibTeX
+@article{song2024less,
+  title={Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs},
+  author={Song, Dingjie and Wang, Wenjun and Chen, Shunian and Wang, Xidong and Guan, Michael and Wang, Benyou},
+  journal={arXiv preprint arXiv:2409.10994},
+  year={2024}
+}
+```