Scholar
Jian Luan
Google Scholar ID: 6Z8RUi4AAAAJ
Toshiba, Microsoft, Xiaomi
LLM
VLM
TTS
Singing Synthesis
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,354
H-index
18
i10-index
27
Publications
20
Co-authors
6
list available
Contact
No contact links provided.
Publications
87 items
DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models
2026
Cited
0
Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning
2026
Cited
0
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
2026
Cited
0
UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation
2026
Cited
0
RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
2026
Cited
0
ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
2026
Cited
0
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
2026
Cited
0
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
2026
Cited
0
Load more
Resume (English only)
Co-authors
6 total
Xu Tan
Principal Researcher and Research Manager, Microsoft
Co-author 2
Zhiyong WU (吴志勇)
Associate Professor, Tsinghua University
Co-author 4
Shengchen Li
Xi'an Jiaotong-Liverpool University
YUANBO HOU
University of Oxford
