Atlas / Reports / Detail
Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities
Audio Language Models report from Stepfun with 10 connected researchers in the LLMpeople atlas.
Connected researchers
Researcher
1 reports
Can Cui
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Xiao Ma
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Zeyi Yan
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Siyao Wang
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Jiale Zhuang
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Yu Guo
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Yizhou Zou
Stepfun
Researcher at StepFun AI working on speech, language, and multimodal learning, including Step-Audio 2.
Researcher
1 reports
Huan Yang
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Ruiqi Song
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.
Researcher
1 reports
Hui Yu
Stepfun
Researcher at Stepfun and coauthor of the Step-Audio 2: Cascaded Multimodal Large Language Models with Versatile Speech Capabilities.