Safe Vision-Language Models with Visual Guard Module (https://huggingface.co/spaces/etri-vilab/Ko-LLaVA)
AI & ML interests
Visual Intelligence, Pretrained Vision-and-Language Model, Embodied AI, Collaborative Agents, Vision Task(Object Detection, Segmentation)
Recent Activity
Organization Card
š„ We are the Visual Intelligence Research Section in the Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, South Korea
| šØ Safe LLaVA/Safe QWen/Safe Gemma : AI Safety-tuned Vision Language Model |
|---|
 |
| šØ KOALA : text-to-image generation | š Ko-LLaVA : Korean Vision-Language Model |
|---|---|
| (feat. Knowledge Distillation based Stable Diffusion XL) | (feat. Korean Large Language and Vision Assistant) |
 |
 |
models
15
etri-vilab/SafeLLaVA-7B
Image-Text-to-Text
ā¢
7B
ā¢
Updated
ā¢
36
ā¢
3
etri-vilab/SafeLLaVA-13B
Image-Text-to-Text
ā¢
13B
ā¢
Updated
ā¢
7
ā¢
3
etri-vilab/SafeQwen2.5-VL-32B
Image-Text-to-Text
ā¢
33B
ā¢
Updated
ā¢
5
ā¢
3
etri-vilab/SafeQwen2.5-VL-7B
Image-Text-to-Text
ā¢
8B
ā¢
Updated
ā¢
3.15k
ā¢
3
etri-vilab/SafeGem-27B
Image-Text-to-Text
ā¢
27B
ā¢
Updated
ā¢
3
etri-vilab/SafeGem-12B
Image-Text-to-Text
ā¢
12B
ā¢
Updated
ā¢
4
ā¢
3
etri-vilab/koala-lightning-1.7b
Text-to-Image
ā¢
Updated
ā¢
32
ā¢
2
etri-vilab/koala-lightning-1b
Text-to-Image
ā¢
Updated
ā¢
37
ā¢
9
etri-vilab/koala-lightning-700m
Text-to-Image
ā¢
Updated
ā¢
58
ā¢
9
etri-vilab/koala-1b
Text-to-Image
ā¢
Updated
ā¢
22
ā¢
16