Scholar
Jiajun Liang
Google Scholar ID: xNxlvjEAAAAJ
MEGVII, KLINGAI
Deep Learning
Computer Vision
Vision-Language Learning
Generative Model
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
4,523
H-index
20
i10-index
25
Publications
20
Co-authors
15
list available
Publications
13 items
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
2026
Cited
0
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
2026
Cited
0
The Velocity Deficit: Initial Energy Injection for Flow Matching
2026
Cited
0
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
2026
Cited
0
FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing
2025
Cited
0
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
2025
Cited
0
VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
2025
Cited
0
Scaling Image and Video Generation via Test-Time Evolutionary Search
2025
Cited
0
Load more
Co-authors
12 total
Yao Tang
Megvii
Haoqiang Fan
Megvii
Cong Yao
Alibaba DAMO Academy
Shuchang Zhou
Megvii Inc.
Yuzhi Wang
Research Engineer @ Megvii Inc.
Pengfei Wan
Head of Kling Video Generation Models, Kuaishou Technology
Xintao Wang
Visual Generation and Interaction Center, Kuaishou Technology
Gongye Liu
The Hong Kong University of Science and Technology
