Scholar

Jun Zhan（詹俊）

Google Scholar ID: GfrhPE8AAAAJ

Computer Science, Fudan University

Multimodal AILarge Language Model

Citations & Impact

All-time

Citations

1,056

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

9 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

First-author paper accepted at ACL 2024: 'VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions'.
Led development of AnyGPT: the first any-to-any unified multimodal LLM based on discrete sequence modeling; received 800+ GitHub stars and coverage by over 10 media outlets including Jiqizhixin.
Co-authored SpeechGPT (EMNLP 2023): the first LLM with intrinsic cross-modal conversational abilities; garnered 1,300+ GitHub stars and wide media attention.
Released SpeechGPT2 (2024): an emotionally intelligent end-to-end spoken dialogue LLM.
Contributed to MOSS: China’s first open-source ChatGPT-like LLM, with 12,000+ GitHub stars.
Best Poster Award at the 3rd HIT-SCIR & THUNLP & FudanNLP Academic Symposium (2024).

Co-authors

11 total