Ceyuan Yang

papers

2,003

total citations

papers (28)

Temporal Pyramid Network for Action Recognition

CVPR 2020arXiv

418

citations

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

ECCV 2024arXiv

264

citations

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

CVPR 2023arXiv

citations

Diffusion Adversarial Post-Training for One-Step Video Generation

ICML 2025arXiv

citations

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

CVPR 2022arXiv

citations

One-Shot Generative Domain Adaptation

ICCV 2023arXiv

citations

Learning Where to Focus for Efficient Video Object Detection

ECCV 2020arXiv

citations

Long Context Tuning for Video Generation

ICCV 2025arXiv

citations

Towards Text-guided 3D Scene Composition

CVPR 2024arXiv

citations

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

ICCV 2025arXiv

citations

Improving GANs with A Dynamic Discriminator

NEURIPS 2022arXiv

citations

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

CVPR 2025arXiv

citations

Improving GAN Equilibrium by Raising Spatial Awareness

CVPR 2022arXiv

citations

LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis

ICCV 2023arXiv

citations

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

CVPR 2025arXiv

citations

GLeaD: Improving GANs With a Generator-Leading Task

CVPR 2023arXiv

citations

Revisiting the Evaluation of Image Synthesis with GANs

NEURIPS 2023arXiv

citations

SMaRt: Improving GANs with Score Matching Regularity

ICML 2024arXiv

citations

Keyframe-Guided Creative Video Inpainting

CVPR 2025

citations

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation

CVPR 2024arXiv

citations

Edicho: Consistent Image Editing in the Wild

ICCV 2025arXiv

citations

Learning Modulated Transformation in GANs

NEURIPS 2023arXiv

citations

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

ICML 2025arXiv

citations

Ceyuan Yang

papers (28)

Temporal Pyramid Network for Action Recognition

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

Instance Localization for Self-Supervised Detection Pretraining

3D-Aware Image Synthesis via Learning Structural and Textural Representations

Generative Hierarchical Features From Synthesizing Images

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

Data-Efficient Instance Generation from Instance Discrimination

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

Diffusion Adversarial Post-Training for One-Step Video Generation

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

One-Shot Generative Domain Adaptation

Learning Where to Focus for Efficient Video Object Detection

Long Context Tuning for Video Generation

Towards Text-guided 3D Scene Composition

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

Improving GANs with A Dynamic Discriminator

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

Improving GAN Equilibrium by Raising Spatial Awareness

LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

GLeaD: Improving GANs With a Generator-Leading Task

Revisiting the Evaluation of Image Synthesis with GANs

SMaRt: Improving GANs with Score Matching Regularity

Keyframe-Guided Creative Video Inpainting

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation

Edicho: Consistent Image Editing in the Wild

Learning Modulated Transformation in GANs

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

papers (28)

Temporal Pyramid Network for Action Recognition

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

Instance Localization for Self-Supervised Detection Pretraining

3D-Aware Image Synthesis via Learning Structural and Textural Representations

Generative Hierarchical Features From Synthesizing Images

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

Data-Efficient Instance Generation from Instance Discrimination

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

Diffusion Adversarial Post-Training for One-Step Video Generation

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

One-Shot Generative Domain Adaptation

Learning Where to Focus for Efficient Video Object Detection

Long Context Tuning for Video Generation

Towards Text-guided 3D Scene Composition

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

Improving GANs with A Dynamic Discriminator

SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

Improving GAN Equilibrium by Raising Spatial Awareness

LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

GLeaD: Improving GANs With a Generator-Leading Task

Revisiting the Evaluation of Image Synthesis with GANs

SMaRt: Improving GANs with Score Matching Regularity

Keyframe-Guided Creative Video Inpainting

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation

Edicho: Consistent Image Editing in the Wild

Learning Modulated Transformation in GANs

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation