The collection of the paper: "R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model"
Xirui Li PRO
AIcell
AI & ML interests
Foundation LLM and VLM
Recent Activity
authored
a paper
about 2 hours ago
What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis
updated
a collection
about 3 hours ago
VisualThinker-R1
updated
a collection
about 3 hours ago
VisualThinker-R1
Organizations
models
5
AIcell/Frankenstein-RL-Frozen-Late
Image-Text-to-Text
•
Updated
•
54
AIcell/Frankenstein-RL-Frozen-Mid
Image-Text-to-Text
•
Updated
•
39
AIcell/Frankenstein-RL-Frozen-Early
Image-Text-to-Text
•
Updated
•
43
AIcell/Frankenstein-RL
Image-Text-to-Text
•
Updated
•
48
AIcell/Frankenstein-IN
Image-Text-to-Text
•
4B
•
Updated
•
59