Songwei Ge
13 papers · 2019–2025 · 5 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (29)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(54)
Venues
Top co-authors
Research topics
Computer Vision
(8)
Deep Learning
(8)
Machine Learning
(6)
Generation
(6)
Artificial Intelligence
(5)
Learning Types Β· Machine Learning
(4)
Models
(4)
Core AI
(3)
Core Methods
(3)
Application Areas
(2)
Architectures
(2)
Learning Paradigms
(2)
Learning Types Β· Deep Learning
(2)
Optimization & Theory
(2)
Techniques
(2)
Keywords
diffusion model
(3)
text-to-image generation
(3)
representation learning
(3)
video generation
(2)
adversarial robustness
(2)
image classification
(2)
contrastive learning
(2)
domain generalization
(2)
convolutional neural network
(2)
text-to-image synthesis
(1)
attention mechanism
(1)
optimal transport
(1)
feature learning
(1)
image translation
(1)
domain adaptation
(1)
distribution shift
(1)
image-to-image translation
(1)
visual representation
(1)
image generation
(1)
zero-shot learning
(1)
Papers
A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation
CVPR 2025
Grounded Text-to-Image Synthesis with Attention Refocusing
CVPR 2024
On the Content Bias in Frechet Video Distance
CVPR 2024
Rethinking Score Distillation as a Bridge Between Image Distributions
NeurIPS 2024
Expressive Text-to-Image Generation with Rich Text
ICCV 2023
Hyperbolic Contrastive Learning for Visual Representations Beyond Objects
CVPR 2023
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
ICCV 2023
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
ECCV 2022
MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration
ECCV 2022
Creative Sketch Generation
ICLR 2021
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
NeurIPS 2021
Shift Invariance Can Reduce Adversarial Robustness
NeurIPS 2021
Learning Robust Global Representations by Penalizing Local Predictive Power
NeurIPS 2019