Jin Xu
Scholar

Jin Xu

Google Scholar ID: COYDNmYAAAAJ
Qwen Team, Alibaba Group
Multimodal InteractionLarge Language ModelSpeech SynthesisVideo/Audio Processing
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
12,379
 
H-index
20
 
i10-index
22
 
Publications
20
 
Co-authors
13
list available
Contact
Emailjxu3425@gmail.comGitHubOpen ↗
Publications
14 items
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
2026
Cited
0
MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training
2026
Cited
0
OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
2026
Cited
0
MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier Auditing
2026
Cited
0
Omni2Web: Benchmarking Audiovisual Website Development
2026
Cited
0
OmniEcho: Spatial Audio Understanding for Embodied Agents
2026
Cited
0
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
2026
Cited
0
Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction
2026
Cited
0
Resume
Academic Achievements
  • Published dozens of papers at top AI conferences including ICLR, ICML, NeurIPS, and KDD.
  • Representative projects: Qwen2.5-Omni, Qwen2-Audio, and Qwen-Audio.
  • 1st Place, KDD Cup AutoGraph Competition (2020).
  • First Prize, Mathematical Contest in Modeling (2015).
  • First Prize, University Students Physics Competition in Parts of the Country (2015).
Co-authors
12 total
Yunfei Chu
Yunfei Chu
Alibaba Group
Tao Qin
Tao Qin
Vice President, Zhongguancun Academy
Xu Tan
Xu Tan
Principal Researcher and Research Manager, Microsoft
Tie-Yan Liu
Tie-Yan Liu
President, Zhongguancun Academy | IEEE Fellow | ACM Fellow | AAIA Fellow
Yichong Leng
Yichong Leng
University of Science and Technology of China
Junyang Lin
Junyang Lin
Qwen Team, Alibaba Group & Peking University
Jian Li
Jian Li
Professor, Tsinghua University
Jingren Zhou
Jingren Zhou
Alibaba Group, Microsoft