Qihang Fan
Scholar

Qihang Fan

Google Scholar ID: 9HGN_c0AAAAJ
Phd Student, Institute of Automation, Chinese Academy of Sciences
computer visionmulti-modal large language modeldeep learning architecture
Google Scholar↗
Citations & Impact
All-time
Citations
432
 
H-index
8
 
i10-index
6
 
Publications
17
 
Co-authors
6
list available
Contact
No contact links provided.
Publications
13 items
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
2026
Cited
0
Random Wins All: Rethinking Grouping Strategies for Vision Tokens
2026
Cited
0
Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
2025
Cited
0
Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning
2025
Cited
0
Vidi2: Large Multimodal Models for Video Understanding and Creation
2025
Cited
0
Rectifying Magnitude Neglect in Linear Attention
2025
Cited
0
Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention
2025
Cited
0
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
2025
Cited
0
Resume (English only)
Co-authors
6 total
Huaibo Huang
Huaibo Huang
NLPR, MAIS, CASIA
Co-author 2
Co-author 2
Mingrui Chen
Mingrui Chen
Institute of Automation, Chinese Academy of Sciences
Haogeng Liu
Haogeng Liu
Tiktok
Yuang Ai
Yuang Ai
MS Student, Institute of Automation, Chinese Academy of Sciences
Co-author 6
Co-author 6