Chaoyue Wang

17

Papers

31

Total Citations

Papers (17)

Decomposing Semantic Shifts for Composed Image Retrieval

One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls

MagicNaming: Consistent Identity Generation by Finding a “Name Space” in T2I Diffusion Models

Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models

Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation

Syntax-Aware Action Targeting for Video Captioning

FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation

PuppeteerGAN: Arbitrary Portrait Animation With Semantic-Aware Appearance Transformation

Modeling Image Composition for Complex Scene Generation

Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition

MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models

FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs

Video Frame Interpolation without Temporal Priors

NeurIPS 2020arXiv

SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders

NeurIPS 2022arXiv

Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation

NeurIPS 2023arXiv

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

NeurIPS 2023arXiv

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

NeurIPS 2023arXiv