Qihang Yu
31 papers · 2018–2026 · 8 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (52) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Gold π£ Hot Topic Early Bird
π¬
Deep Specialist
(10)
π§
Keyword Pioneer
π
Grand Slam
π₯
Mega-Team Β· Squad
π€
Dynamic Duo
(20)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
ποΈ
Keyword Collector
(135)
Top co-authors
Research topics
Keywords
semantic segmentation
(8)
image segmentation
(6)
medical imaging
(4)
transformer architecture
(4)
image generation
(4)
panoptic segmentation
(4)
flow matching
(4)
convolutional neural network
(4)
representation learning
(3)
diffusion model
(3)
object detection
(3)
mask transformer
(3)
feature extraction
(2)
generative model
(2)
efficient computing
(2)
neural architecture search
(2)
text-to-image generation
(2)
computer vision
(2)
model compression
(2)
vision transformer
(2)
Papers
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
CVPR 2026
Frequency-Aware Flow Matching for High-Quality Image Generation
CVPR 2026
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
ICCV 2025
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
ICCV 2025
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
ICML 2025
FlowTok: Flowing Seamlessly Across Text and Image Tokens
ICCV 2025
Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation
ICCV 2025
Randomized Autoregressive Visual Generation
ICCV 2025
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
NeurIPS 2024
An Image is Worth 32 Tokens for Reconstruction and Generation
NeurIPS 2024
COCONut: Modernizing COCO Segmentation
CVPR 2024
Towards Open-Ended Visual Recognition with Large Language Models
ECCV 2024
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation
WACV 2024
ViTamin: Designing Scalable Vision Models in the Vision-Language Era
CVPR 2024
CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans
ICCV 2023
Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation
CVPR 2023
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
NeurIPS 2023
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
ICLR 2023
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
NeurIPS 2023
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
CVPR 2022
k-Means Mask Transformer
ECCV 2022
"PartImageNet: A Large, High-Quality Dataset of Parts"
ECCV 2022
TubeFormer-DeepLab: Video Mask Transformer
CVPR 2022
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks
AAAI 2021
Glance-and-Gaze Vision Transformer
NeurIPS 2021
Mask Guided Matting via Progressive Refinement Network
CVPR 2021
Shape-Texture Debiased Neural Network Training
ICLR 2021
C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
CVPR 2020
Neural Architecture Search for Lightweight Non-Local Networks
CVPR 2020
When Radiology Report Generation Meets Knowledge Graph
AAAI 2020
Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation
CVPR 2018