Shikun Liu
Scholar

Shikun Liu

Google Scholar ID: Y9E1GbEAAAAJ
Research Scientist, Meta AI
Machine LearningComputer Vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
3,233
 
H-index
11
 
i10-index
11
 
Publications
13
 
Co-authors
20
list available
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
10 items
EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
2026
Cited
0
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
2025
Cited
0
Scaling Zero-Shot Reference-to-Video Generation
2025
Cited
0
Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
2025
Cited
0
Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings
2025
Cited
0
Scaling Sequence-to-Sequence Generative Neural Rendering
2025
Cited
0
RoFt-Mol: Benchmarking Robust Fine-Tuning with Molecular Graph Foundation Models
2025
Cited
0
Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
2025
Cited
0
Resume (English only)
Research Experience
  • AI Research Scientist at Meta GenAI
Background
  • Research Focus: Building AI systems to perceive, reason and act across diverse tasks and modalities.
Co-authors
20 total
Andrew Davison
Andrew Davison
Professor of Robot Vision, Department of Computing, Imperial College London
Edward Johns
Edward Johns
Associate Professor in Robot Learning at Imperial College London
Edgar Sucar
Edgar Sucar
University of Oxford
Xin Kong
Xin Kong
Ph.D. Student, Department of Computing, Imperial College London
Marwan Taher
Marwan Taher
Imperial College London
C Lee Giles
C Lee Giles
Pennsylvania State University
Anima Anandkumar
Anima Anandkumar
California Institute of Technology and NVIDIA
Linxi "Jim" Fan
Linxi "Jim" Fan
NVIDIA, https://jimfan.me