Kaichen Zhang
Scholar

Kaichen Zhang

Google Scholar ID: 4_mo8-oAAAAJ
Nanyang Technological University
VLMsComputer VisionMulti-modality
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,747
 
H-index
6
 
i10-index
6
 
Publications
8
 
Co-authors
6
list available
Contact
No contact links provided.
Publications
17 items
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding
2026
Cited
0
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation
2026
Cited
0
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
2026
Cited
0
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
2026
Cited
0
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
2026
Cited
0
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
2026
Cited
0
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
2026
Cited
0
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
2026
Cited
0
Resume (English only)
Co-authors
6 total
Brian (Bo) Li
Brian (Bo) Li
PhD Student@NTU, Singapore
Ziwei Liu
Ziwei Liu
Associate Professor, Nanyang Technological University
Yuanhan Zhang
Yuanhan Zhang
PhD Candidate, MMLab@NTU
Peiyuan Zhang
Peiyuan Zhang
University of California, San Diego
Jingkang Yang
Jingkang Yang
PhD, MMLab@NTU
Fanyi Pu
Fanyi Pu
MMLab@NTU, Singapore