Qihang Fan
8 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
Venues
Top co-authors
Research topics
Deep Learning
(7)
Machine Learning
(5)
Architectures
(5)
Application Areas
(4)
Computer Vision
(2)
Analysis
(2)
Learning Types
(2)
Models
(2)
Techniques
(2)
Artificial Intelligence
(1)
Reinforcement Learning
(1)
Core AI · Artificial Intelligence
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Methods
(1)
Keywords
vision transformer
(6)
image classification
(4)
linear attention
(2)
object detection
(1)
mathematical reasoning
(1)
multimodal learning
(1)
model architecture
(1)
instance segmentation
(1)
efficient computing
(1)
generative model
(1)
feature map
(1)
vision-language model
(1)
semantic clustering
(1)
point cloud processing
(1)
group relative policy optimization
(1)
multimodal pretraining
(1)
trajectory diversity
(1)
token clustering
(1)
large language model
(1)
neural network
(1)
Papers
Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
CVPR 2026
Random Wins All: Rethinking Grouping Strategies for Vision Tokens
CVPR 2026
Breaking the Low-Rank Dilemma of Linear Attention
CVPR 2025
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
EMNLP 2025
Rectifying Magnitude Neglect in Linear Attention
ICCV 2025
Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
ICCV 2025
RMT: Retentive Networks Meet Vision Transformers
CVPR 2024
Lightweight Vision Transformer with Bidirectional Interaction
NeurIPS 2023