add Puffin-4M

README.md

@@ -101,6 +101,7 @@ social network, flow chart, mind map). It's also important for LLM or VLM to bui
 | Title                                                        |                         Introduction                         |    Date    |                           Code                           |
 | :----------------------------------------------------------- | :----------------------------------------------------------: | :--------: | :------------------------------------------------------: |
 |  <br/>[Visual Spatial Tuning](https://arxiv.org/pdf/2511.05491) |   <img width="700" alt="image" src="imgs/VST.png">   | 2025-11 |          [Github](https://github.com/Yangr116/VST) |
+|  <br/>[Puffin-4M: Benchmarking Multimodal Spatial Intelligence and Reasoning with 4 Million Vision-Language-Camera Triplets](https://arxiv.org/pdf/2510.08673) |   <img width="700" alt="image" src="imgs/Puffin-4M.png">   | 2025-10 |          [Github](https://github.com/KangLiao929/Puffin) |
 |  <br/>[DSI-Bench: A Benchmark for Dynamic Spatial Intelligence](https://arxiv.org/abs/2510.18873) |   <img width="700" alt="image" src="imgs/DSI-Bench.png">   | 2025-10 |          [Github](https://dsibench.github.io/) |
 |  <br/>[Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes](https://arxiv.org/pdf/2510.19400) |   <img width="700" alt="image" src="imgs/MV-RoboBench.png">   | 2025-10 |           - |
 |  <br/>[NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions](https://arxiv.org/abs/2510.08173) |   <img width="700" alt="image" src="imgs/NavSpace.png">   | 2025-10 |        [Github](https://navspace.github.io/#NavSpace-Leaderboard)  |