
Hi! I am Kexin (Caasi) HUANG, a second-year master’s student in Computer Science at Fudan University, supervised by Prof. Xipeng QIU. Before that, I served as a research assistant at Shanghai Artificial Intelligence Laboratory, and I received my bachelor’s degree in Computer Science at Fudan University. My current research interest primarily focuses on Multimodal LLM.
🙋 Expected to graduate in 2027, feel free to connect!
Email / Google Scholar / GitHub / LinkedIn
You can find the full list of papers at Google Scholar.
(Chronologically listed, most recent first. * denotes equal contribution)
MOSS-VoiceGenerator
Website / GitHub / Huggingface
Core Contributor
WESR: Scaling and Evaluating Word-level Event-Speech Recognition (arXiv 26’)
Paper / GitHub
Chenchen Yang, Kexin Huang, Liwei Fan, Qian Tu, Botian Jiang, Dong Zhang, Linqi Yin, Shimin Li, Zhaoye Fei, Qinyuan Cheng, Xipeng Qiu
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems (arXiv 25’)
Paper / GitHub
Kexin Huang, Qian Tu, Liwei Fan, Chenchen Yang, Dong Zhang, Shimin Li, Zhaoye Fei, Qinyuan Cheng, Xipeng Qiu
Paopao
4-year-old British Shorthair
Bully at home, coward outside
Meimei
3-year-old Ragdoll
Graceful and poised, with a laidback vibe
Glad to See You Here:D