Improve model card and metadata

README.md

@@ -1,40 +1,53 @@
 ---
 license: bsd-3-clause
 pipeline_tag: video-text-to-text
+library_name: transformers
+base_model: Qwen/Qwen2-VL-2B-Instruct
 ---
 
 # VideoMind-2B-FT-QVHighlights
 
 <div style="display: flex; gap: 5px;">
+  <a href="https://huggingface.co/papers/2503.13444" target="_blank"><img src="https://img.shields.io/badge/Paper-HF--Papers-yellow"></a>
   <a href="https://arxiv.org/abs/2503.13444" target="_blank"><img src="https://img.shields.io/badge/arXiv-2503.13444-red"></a>
   <a href="https://videomind.github.io/" target="_blank"><img src="https://img.shields.io/badge/Project-Page-brightgreen"></a>
+  <a href="https://github.com/yeliudev/VideoMind" target="_blank"><img src="https://img.shields.io/badge/GitHub-Code-blue"></a>
   <a href="https://github.com/yeliudev/VideoMind/blob/main/README.md" target="_blank"><img src="https://img.shields.io/badge/License-BSD--3--Clause-purple"></a>
-  <a href="https://github.com/yeliudev/VideoMind" target="_blank"><img src="https://img.shields.io/github/stars/yeliudev/VideoMind"></a>
 </div>
 
-VideoMind is a multi-modal agent framework that enhances video reasoning by emulating *human-like* processes, such as *breaking down tasks*, *localizing and verifying moments*, and *synthesizing answers*.
+**VideoMind** is a multi-modal agent framework that enhances video reasoning by emulating *human-like* processes, such as *breaking down tasks*, *localizing and verifying moments*, and *synthesizing answers*.
+
+This repository contains the fine-tuned LoRA adapter (specifically the **Grounder** role for temporal event localization) for the 2B version of the framework, trained on the **QVHighlights** dataset. It is based on the paper [VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning](https://huggingface.co/papers/2503.13444).
 
 ## 🔖 Model Details
 
 ### Model Description
 
-- **Model type:** Multi-modal Large Language Model
+- **Model type:** Multi-modal Large Language Model (LoRA Adapter)
+- **Base Model:** [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct)
+- **Role:** Grounder (Temporal Event Localization)
 - **Language(s):** English
 - **License:** BSD-3-Clause
 
-### More Details
+### Framework Overview
+
+VideoMind identifies four essential capabilities for grounded video reasoning:
+1. **Planner:** Coordinates roles.
+2. **Grounder:** Temporal event localization.
+3. **Verifier:** Assesses event candidates.
+4. **Answerer:** Question answering.
 
-Please refer to our [GitHub Repository](https://github.com/yeliudev/VideoMind) for more details about this model.
+This specific checkpoint is the Grounder specialized for the QVHighlights task using the Chain-of-LoRA mechanism.
 
 ## 📖 Citation
 
 Please kindly cite our paper if you find this project helpful.
 
-```
+```bibtex
 @inproceedings{liu2026videomind,
   title={VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning},
   author={Liu, Ye and Lin, Kevin Qinghong and Chen, Chang Wen and Shou, Mike Zheng},
   booktitle={International Conference on Learning Representations (ICLR)},
   year={2026}
 }
-```
+```