AI & ML interests

Visual Intelligence, Pretrained Vision-and-Language Model, Embodied AI, Collaborative Agents, Vision Task(Object Detection, Segmentation)

Organization Card

Community About org cards

🔥 We are the Visual Intelligence Research Section in the Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, South Korea

Generate images from text using a lightweight SDXL model

Safe-VLM

🚀

Answer questions about images with text prompts

models 18

etri-vilab/MultiHopSpatial-Qwen3-VL-32B-Instruct

Image-Text-to-Text • 33B • Updated Jul 18 • 14 • 1

etri-vilab/MultiHopSpatial-Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Jul 18 • 14 • 1

etri-vilab/MultiHopSpatial-Qwen3-VL-4B-Instruct

Image-Text-to-Text • 4B • Updated Jul 18 • 70 • 3

etri-vilab/SafeLLaVA-7B

Image-Text-to-Text • 7B • Updated Dec 5, 2025 • 73 • 3

etri-vilab/SafeLLaVA-13B

Image-Text-to-Text • 13B • Updated Nov 24, 2025 • 11 • 3

etri-vilab/SafeQwen2.5-VL-32B

Image-Text-to-Text • 33B • Updated Nov 17, 2025 • 15 • 3

etri-vilab/SafeQwen2.5-VL-7B

Image-Text-to-Text • 8B • Updated Nov 17, 2025 • 30 • 3

etri-vilab/SafeGem-27B

Image-Text-to-Text • 27B • Updated Nov 17, 2025 • 13 • 3

etri-vilab/SafeGem-12B

Image-Text-to-Text • 12B • Updated Nov 17, 2025 • 13 • 3

etri-vilab/koala-lightning-1.7b

Text-to-Image • 2B • Updated Nov 26, 2024 • 11 • 2

View 18 models

datasets 4

etri-vilab/MultihopSpatial

Viewer • Updated Jul 28 • 15.8k • 950 • 6

etri-vilab/holisafe-bench

Viewer • Updated Jun 1 • 4.03k • 987 • 11

etri-vilab/Ko-LAION-Aesthetics-10M

Viewer • Updated Jan 15, 2025 • 10M • 61

etri-vilab/Ko-LLaVA-Instruct-150K

Viewer • Updated Jan 15, 2025 • 158k • 21

AI & ML interests

Team members 11

Collections 4

Safe-VLM

Safe-VLM

spaces 3 Sort: Recently updated

KOALA

Safe-VLM

models 18 Sort: Recently updated

datasets 4 Sort: Recently updated

spaces 3

models 18

datasets 4