Rationale-aided Efficient 7B size Large Language and Vision Models. Let's enjoy it!
Byung-Kwan Lee
BK-Lee
AI & ML interests
Computer Vision, Machine Learning, Vision Language Models
Recent Activity
upvoted
a
paper
about 3 hours ago
I-Con: A Unifying Framework for Representation Learning
upvoted
a
paper
1 day ago
TTRL: Test-Time Reinforcement Learning
upvoted
a
paper
2 days ago
Eagle 2.5: Boosting Long-Context Post-Training for Frontier
Vision-Language Models
Organizations
Collections
4
spaces
3
models
11

BK-Lee/Meteor-MLM
Image-Text-to-Text
•
Updated
•
25
•
12

BK-Lee/CoLLaVO-7B
Image-Text-to-Text
•
Updated
•
4
•
21

BK-Lee/MoAI-7B
Image-Text-to-Text
•
Updated
•
8
•
45

BK-Lee/Phantom-7B
Updated
•
28
•
6

BK-Lee/Phantom-3.8B
Updated
•
11
•
1

BK-Lee/Phantom-1.8B
Updated
•
9
•
1

BK-Lee/Phantom-0.5B
Updated
•
3
•
4

BK-Lee/TroL-7B
Updated
•
44
•
7

BK-Lee/TroL-3.8B
Text Generation
•
Updated
•
13
•
2

BK-Lee/TroL-1.8B
Updated
•
26
•
3