Update README.md
Browse files
README.md
CHANGED
|
@@ -27,5 +27,9 @@ license: apache-2.0
|
|
| 27 |
## Model Overview
|
| 28 |
|
| 29 |
OpenAI's plan to release a SOTA text-in, text-out toggleable reasoning LLM means the most performant Vision-Language Model (VLM) will likely be based
|
| 30 |
-
on this llm backbone.
|
|
|
|
|
|
|
| 31 |
as well as the step-by-step instructions are [in the works](https://github.com/andrewliao11/Q-Spatial-Bench-code/blob/main/prompt_templates/spatial_prompt_steps.txt)
|
|
|
|
|
|
|
|
|
| 27 |
## Model Overview
|
| 28 |
|
| 29 |
OpenAI's plan to release a SOTA text-in, text-out toggleable reasoning LLM means the most performant Vision-Language Model (VLM) will likely be based
|
| 30 |
+
on this llm backbone.
|
| 31 |
+
|
| 32 |
+
Meanwhile, updated methods of reasoning synthesis which include improvements to localization & captioning using "Describe Anything"
|
| 33 |
as well as the step-by-step instructions are [in the works](https://github.com/andrewliao11/Q-Spatial-Bench-code/blob/main/prompt_templates/spatial_prompt_steps.txt)
|
| 34 |
+
|
| 35 |
+
Check out [SpaceThinker](https://huggingface.co/remyxai/SpaceThinker-Qwen2.5VL-3B) for more on the cutting-edge of quantitative spatial reasoning.
|