From Pixels to Words -- Towards Native Vision-Language Primitives at Scale
Haiwen Diao
Paranioar
AI & ML interests
Vision-and-Language, Parameter-efficient Transfer Learning, Multi-modal Large Language Model
Recent Activity
commented on
a paper
1 day ago
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
upvoted
a
paper
22 days ago
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
Organizations
models
6
Paranioar/NEO1_0-2B-PT
Image-Text-to-Text
•
3B
•
Updated
•
12
•
1
Paranioar/NEO1_0-2B-MT
Image-Text-to-Text
•
3B
•
Updated
•
12
Paranioar/NEO1_0-2B-SFT
Image-Text-to-Text
•
3B
•
Updated
•
96
•
8
Paranioar/NEO1_0-9B-PT
Image-Text-to-Text
•
10B
•
Updated
•
3
Paranioar/NEO1_0-9B-MT
Image-Text-to-Text
•
10B
•
Updated
•
12
Paranioar/NEO1_0-9B-SFT
Image-Text-to-Text
•
10B
•
Updated
•
66
•
5
datasets
0
None public yet