Yizhi Song
Scholar

Yizhi Song

Google Scholar ID: IUj5R3EAAAAJ
Research Scientist, Bytedance / Tiktok
Image generationGenerative AIMLLMDiffusion
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
282
 
H-index
7
 
i10-index
6
 
Publications
15
 
Co-authors
13
list available
Contact
No contact links provided.
Publications
10 items
PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment
2026
Cited
0
ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing
arXiv.org · 2026
Cited
0
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
2025
Cited
0
DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces
2025
Cited
0
Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation
2025
Cited
0
MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models
2025
Cited
0
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
2025
Cited
0
Generative AI for Cel-Animation: A Survey
2025
Cited
0
Resume (English only)
Co-authors
13 total
Daniel G. Aliaga
Daniel G. Aliaga
Associate Professor of Computer Science, Purdue University
Zhifei Zhang
Zhifei Zhang
Adobe Research
Soo Ye Kim
Soo Ye Kim
Research Scientist, Adobe Research
Zhe L. Lin
Zhe L. Lin
Senior Principal Scientist, Adobe Research
Scott Cohen
Scott Cohen
Adobe Research
Brian Price
Brian Price
Adobe Research
Jianming Zhang
Jianming Zhang
Senior Principal Research Scientist, Adobe
Liu He
Liu He
Purdue University