Qihang Yu
Scholar

Qihang Yu

Google Scholar ID: 7zZdZxsAAAAJ
Research Scientist, Amazon FAR
Computer VisionMedical Image AnalysisDeep Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
10,778
 
H-index
28
 
i10-index
41
 
Publications
20
 
Co-authors
18
list available
Contact
Emailyucornetto@gmail.comGitHubOpen ↗
Publications
12 items
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
2026
Cited
0
Autoregressive Image Generation with Masked Bit Modeling
2026
Cited
0
MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation
2026
Cited
1
ThinkRec: Thinking-based recommendation via LLM
2025
Cited
0
Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
2025
Cited
0
ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction
2025
Cited
0
FlowTok: Flowing Seamlessly Across Text and Image Tokens
2025
Cited
0
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
2025
Cited
0
Resume (English only)
Academic Achievements
  • 1 paper accepted to ECCV 2024
  • 2 papers accepted to CVPR 2024
  • 2 papers accepted to NeurIPS 2023
  • 1 oral paper accepted to WACV 2024
  • 1 paper accepted to ICCV 2023
  • 1 paper accepted to CVPR 2023
  • 1 paper accepted to ICLR 2023
  • 2 papers accepted to ECCV 2022, with one CVPR 2022 paper as Oral
  • Notable publications include 'An Image is Worth 32 Tokens for Reconstruction and Generation' (NeurIPS 2024), 'Convolutions Die Hard' (NeurIPS 2023), and 'k-means Mask Transformer'
Co-authors
18 total
Alan Yuille
Alan Yuille
Professor of Cognitive Science and Computer Science, Johns Hopkins University
Yuyin Zhou
Yuyin Zhou
Assistant Professor, Computer Science and Engineering, Genomics Institute, UC Santa Cruz
Liang-Chieh Chen
Liang-Chieh Chen
Senior Principal Scientist, Amazon FAR, LA
Jieneng Chen
Jieneng Chen
Johns Hopkins University
Ju He
Ju He
Applied Scientist, Amazon Frontier AI & Robotics (FAR)
Siyuan Qiao
Siyuan Qiao
Research Scientist, Google DeepMind
Lingxi Xie (谢凌曦)
Lingxi Xie (谢凌曦)
Senior Researcher, Huawei
Huiyu Wang
Huiyu Wang
Research Scientist, FAIR, Meta