Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning Paper • 2504.16656 • Published Apr 23 • 57
Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning Paper • 2505.07263 • Published May 12 • 29
CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs Paper • 2505.24120 • Published 14 days ago • 48