Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,7 @@ Spatial-SSRL-7B is a large vision-language model targeting spatial understanding
|
|
| 25 |
paradigm which can scale RLVR efficiently. The model demonstrates strong spatial intelligence while preserving the original general visual capabilities of the base model.
|
| 26 |
|
| 27 |
## 📢 News
|
|
|
|
| 28 |
- 🚀 [2026/02/25] We have released the [🤗Spatial-SSRL-3B Model](https://huggingface.co/internlm/Spatial-SSRL-3B), initialized from Qwen2.5-VL-3B-Instruct.
|
| 29 |
- 🚀 [2026/02/21] Our work has been accepted by CVPR 2026.
|
| 30 |
- 🚀 [2025/11/24] We have released the [🤗Spatial-SSRL-Qwen3VL-4B Model](https://huggingface.co/internlm/Spatial-SSRL-Qwen3VL-4B), initialized from Qwen3-VL-4B-Instruct.
|
|
|
|
| 25 |
paradigm which can scale RLVR efficiently. The model demonstrates strong spatial intelligence while preserving the original general visual capabilities of the base model.
|
| 26 |
|
| 27 |
## 📢 News
|
| 28 |
+
- 🚀 [2026/04/05] We have released the training code of Spatial-SSRL.
|
| 29 |
- 🚀 [2026/02/25] We have released the [🤗Spatial-SSRL-3B Model](https://huggingface.co/internlm/Spatial-SSRL-3B), initialized from Qwen2.5-VL-3B-Instruct.
|
| 30 |
- 🚀 [2026/02/21] Our work has been accepted by CVPR 2026.
|
| 31 |
- 🚀 [2025/11/24] We have released the [🤗Spatial-SSRL-Qwen3VL-4B Model](https://huggingface.co/internlm/Spatial-SSRL-Qwen3VL-4B), initialized from Qwen3-VL-4B-Instruct.
|