Songwei Ge
13 papers · 2019–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (9) 🌍 Conference Polyglot (5) 🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (5)
🏃
Academic Marathon
(6)
🐝
Cross-Pollinator
(9)
🌈
Renaissance Researcher
(5)
💎
Century Club
(13)
🔥
Unstoppable
(5)
🗃️
Keyword Collector
(51)
Conferences
CVPR (4)
NIPS (4)
ECCV (2)
ICCV (2)
ICLR (1)
Top co-authors
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
Rethinking Score Distillation as a Bridge Between Image Distributions
NIPS 2024
Grounded Text-to-Image Synthesis with Attention Refocusing
CVPR 2024
On the Content Bias in Frechet Video Distance
CVPR 2024
Hyperbolic Contrastive Learning for Visual Representations Beyond Objects
CVPR 2023
Expressive Text-to-Image Generation with Rich Text
ICCV 2023
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
ICCV 2023
MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration
ECCV 2022
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
ECCV 2022
Creative Sketch Generation
ICLR 2021
Shift Invariance Can Reduce Adversarial Robustness
NIPS 2021
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
NIPS 2021
Learning Robust Global Representations by Penalizing Local Predictive Power
NIPS 2019