Xiefan Guo
7 papers · 2021–2026 · 2 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(17)
Top co-authors
Research topics
Keywords
diffusion model
(3)
text-to-image generation
(2)
image generation
(2)
knowledge transfer
(1)
latent space
(1)
texture synthesis
(1)
scene graph generation
(1)
reward function
(1)
image inpainting
(1)
generative model
(1)
feature aggregation
(1)
model alignment
(1)
gradient backpropagation
(1)
text-to-image diffusion
(1)
text-to-image synthesis
(1)
real-time inference
(1)
long-tail distribution
(1)
latent diffusion model
(1)
cross-attention map
(1)
image restoration
(1)
Papers
CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
CVPR 2026
Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
CVPR 2025
ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
ICCV 2025
InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
CVPR 2024
Leveraging Predicate and Triplet Learning for Scene Graph Generation
CVPR 2024
ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo
CVPR 2022
Image Inpainting via Conditional Texture and Structure Dual Generation
ICCV 2021