Xiaokang Chen is a researcher on DeepSeek’s multimodal team, exploring vision, grounding, pointing, and reasoning capabilities in multimodal models. He previously completed bachelor’s and Ph.D. studies at Peking University.
Xiaokang Chen is a researcher on DeepSeek’s multimodal team, exploring vision, grounding, pointing, and reasoning capabilities in multimodal models. He previously completed bachelor’s and Ph.D. studies at Peking University.
Career
AGI Researcher at DeepSeek from 2024-04 to PresentWorks on multimodal pre-training and post-training for DeepSeek's foundation models.