Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Paper
•
2504.16656
•
Published
•
57
Skywork-R1V2
Multimodal Hybrid Reinforcement Learning for Reasoning
-
-
Skywork/Skywork-R1V2-38B
Image-Text-to-Text • 38B • Updated • 190 • 126 -
Skywork/Skywork-R1V2-38B-AWQ
Image-Text-to-Text • Updated • 53 • 11 -
Skywork/Skywork-VL-Reward-7B
Image-Text-to-Text • 8B • Updated • 530 • 46 -
Skywork/CSVQA
Viewer • Updated • 1.38k • 125 • 6 -
Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
Paper • 2505.07263 • Published • 30 -
CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs
Paper • 2505.24120 • Published • 49