a

README.md

@@ -7,6 +7,10 @@
 **Visual Instruction Tuning** <br>
 [Haotian Liu*](https://hliu.cc), [Chunyuan Li*](https://chunyuan.li/), [Qingyang Wu](https://scholar.google.ca/citations?user=HDiw-TsAAAAJ&hl=en/), [Yong Jae Lee](https://pages.cs.wisc.edu/~yongjaelee/) (*Equal Contribution)
 
+<p align="center">
+    <img src="images/llava_logo.png" width="50%"> <br>
+    Generated by <a href="https://gligen.github.io/">GLIGEN</a> via "a cute lava llama with glasses" and box prompt
+</p>
 
 
 ## Release
@@ -312,4 +316,6 @@ If you find LLaVA useful for your your research and applications, please cite us
 
 - [Instruction Tuning with GPT-4](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
 
-- For future project ideas, checkout the [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything) to detect, segment, and generate anything by marrying [Grounding DINO](https://github.com/IDEA-Research/GroundingDINO) and [Segment-Anything](https://github.com/facebookresearch/segment-anything).
+For future project ideas, pleae check out:
+- [SEEM: Segment Everything Everywhere All at Once](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once)
+- [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything) to detect, segment, and generate anything by marrying [Grounding DINO](https://github.com/IDEA-Research/GroundingDINO) and [Segment-Anything](https://github.com/facebookresearch/segment-anything).