Designing Scalable Vision Models in the Vision-language Era. The best performing model is 'jienengchen/ViTamin-XL-384px'.
Jieneng Chen
jienengchen
AI & ML interests
multi-modal LLMs
Recent Activity
upvoted
a
paper
about 1 month ago
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition
liked
a model
3 months ago
moonshotai/Kimi-K2-Thinking
liked
a Space
3 months ago
CSU-JPG/VCode
Organizations
models
17
jienengchen/ViTamin-XL-384px-s13B
Updated
jienengchen/ViTamin-XL-256px-s13B
Feature Extraction
•
Updated
•
1
jienengchen/ViTamin-XL-256px
Feature Extraction
•
Updated
•
1
jienengchen/ViTamin-L-384px
Feature Extraction
•
Updated
•
2
jienengchen/ViTamin-XL-336px
Feature Extraction
•
Updated
•
2
•
1
jienengchen/ViTamin-L-256px
Feature Extraction
•
Updated
•
127
jienengchen/ViTamin-L2-224px
Feature Extraction
•
Updated
jienengchen/ViTamin-L-224px
Feature Extraction
•
Updated
•
2
jienengchen/ViTamin-L-336px
Feature Extraction
•
Updated
•
4
jienengchen/ViTamin-L2-384px
Feature Extraction
•
Updated
•
3
datasets
0
None public yet