hitsmy/Qwen2-VL-2B-Instruct-SFT
Image-to-Text
•
2B
•
Updated
Mingyang Song
hitsmy
AI & ML interests
LVLMs
Recent Activity
upvoted
a
paper
17 days ago
Reasoning over Boundaries: Enhancing Specification Alignment via
Test-time Delibration
upvoted
a
paper
about 2 months ago
Speed Always Wins: A Survey on Efficient Architectures for Large
Language Models
upvoted
a
paper
about 2 months ago
StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation
Organizations
