Yuhang Ma
Scholar

Yuhang Ma

Google Scholar ID: 0I5QGngAAAAJ
Bytedance, University College London
Generative AIMulti-module Pretraining(Conditional) Text-to-image Generation (AIGC)
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
95
 
H-index
4
 
i10-index
2
 
Publications
7
 
Co-authors
5
list available
Contact
No contact links provided.
Publications
16 items
Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?
2026
Cited
0
RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing
2026
Cited
0
Flow matching-based generative models for MIMO channel estimation
2025
Cited
0
EVTAR: End-to-End Try on with Additional Unpaired Visual Reference
2025
Cited
0
CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities
2025
Cited
0
NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion Transformer
2025
Cited
0
FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer
2025
Cited
0
HPSv3: Towards Wide-Spectrum Human Preference Score
2025
Cited
0
Resume (English only)
Co-authors
5 total
Jingqun Tang
Jingqun Tang
ByteDance Inc.
Dimitrios Kanoulas
Dimitrios Kanoulas
Professor in Robotics and AI, UKRI FLF, University College London (UCL), Archimedes/Athena RC
Mushui Liu
Mushui Liu
Zhejiang University
Keqiang Sun
Keqiang Sun
The Chinese University of Hong Kong
Rongsheng Zhang
Rongsheng Zhang
Fuxi AI Lab, NetEase Inc., Hangzhou, China