Pioneering Perception Policy with Reinforcement Learning
Linkangheng
Kangheng
AI & ML interests
None yet
Recent Activity
updated
a collection
4 days ago
Perception-R1
updated
a dataset
4 days ago
Kangheng/PR1-Evaluations
published
a dataset
4 days ago
Kangheng/PR1-Evaluations
Organizations
None yet
Collections
1
models
7
Kangheng/PR1-Qwen2-VL-2B-OCR
Updated
•
31
•
3
Kangheng/PR1-Qwen2-VL-2B-Counting
Updated
•
5
•
4
Kangheng/PR1-Qwen2-VL-2B-Grounding
Updated
•
6
•
4
Kangheng/PR1-Qwen2.5-VL-3B-Detection
Updated
•
6
•
4
Kangheng/Video-UTR-7b
Video-Text-to-Text
•
Updated
•
2
•
8
Kangheng/Merlin-chat
Text Generation
•
Updated
Kangheng/Merlin
Text Generation
•
Updated
datasets
7
Kangheng/PR1-Evaluations
Viewer
•
Updated
•
1.28k
•
9
•
4
Kangheng/PR1-Datasets-Grounding
Viewer
•
Updated
•
320k
•
123
•
6
Kangheng/Videochat2-PPL
Updated
•
6
Kangheng/UTR-Data
Updated
•
7
Kangheng/refcocog
Viewer
•
Updated
•
14.5k
•
286
Kangheng/refcocop
Viewer
•
Updated
•
21.4k
•
34
Kangheng/refcoco
Viewer
•
Updated
•
21.6k
•
176
•
1