ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Songwei Ge

Songwei Ge

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 12:57 AM AMS

10

papers

1,087

total citations

papers (10)

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer

Grounded Text-to-Image Synthesis with Attention Refocusing

Expressive Text-to-Image Generation with Rich Text

Robust Contrastive Learning Using Negative Samples with Diminished Semantics

NEURIPS 2021arXiv

Hyperbolic Contrastive Learning for Visual Representations Beyond Objects

On the Content Bias in Fréchet Video Distance

Shift Invariance Can Reduce Adversarial Robustness

NEURIPS 2021arXiv

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation