The data and models of the FIRM series.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling
Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
models 9
VisionXLab/FIRM-Video-8B-InternVL3
Image-Text-to-Text • 8B • Updated • 12
VisionXLab/FIRM-Video-8B-Qwen3VL
Image-Text-to-Text • 9B • Updated • 12
VisionXLab/Point2RBox-v2-jittor
Object Detection • Updated
VisionXLab/Point2RBox-v3-jittor
Object Detection • Updated
VisionXLab/FIRM-Qwen-Edit
Updated
VisionXLab/FIRM-SD3.5
Updated
VisionXLab/FIRM-Gen-8B
Image-Text-to-Text • 770k • Updated • 13 • 1
VisionXLab/FIRM-Edit-8B
Image-Text-to-Text • 770k • Updated • 13 • 1
VisionXLab/ProCLIP
Image-Text-to-Text • Updated • 1
datasets 12
VisionXLab/FIRM-Video_BoN_videos
Preview • Updated • 27
VisionXLab/FIRM-Video-Bench
Viewer • Updated • 251 • 79
VisionXLab/FIRM-Video
Viewer • Updated • 1.58M • 125
VisionXLab/RSDet-datasets
Preview • Updated • 35 • 2
VisionXLab/DisciplineGen-1M
Viewer • Updated • 1.1M • 835 • 5
VisionXLab/Moment-Video
Viewer • Updated • 1k • 155 • 2
VisionXLab/GRADE
Viewer • Updated • 1.04k • 495 • 8
VisionXLab/FIRM-Bench
Viewer • Updated • 8 • 97
VisionXLab/FIRM-Edit-Consistency
Viewer • Updated • 180k • 613
VisionXLab/FIRM-Edit-Instruction
Viewer • Updated • 190k • 606