Yiren Song

Affiliations

NUS

papers

369

total citations

papers (10)

SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation

CVPR 2024arXiv

125

citations

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

ICCV 2025arXiv

citations

Stable-Hair: Real-World Hair Transfer via Diffusion Model

AAAI 2025arXiv

citations

Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks

ICCV 2025arXiv

citations

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation

CVPR 2025arXiv

citations

DiffSim: Taming Diffusion Models for Evaluating Visual Similarity

ICCV 2025arXiv

citations

ArtEditor: Learning Customized Instructional Image Editor from Few-Shot Examples

ICCV 2025

citations

Yiren Song

Affiliations

papers (10)

SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

Stable-Hair: Real-World Hair Transfer via Diffusion Model

Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks

Image Watermarks are Removable using Controllable Regeneration from Clean Noise

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

FonTS: Text Rendering With Typography and Style Controls

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation

DiffSim: Taming Diffusion Models for Evaluating Visual Similarity

ArtEditor: Learning Customized Instructional Image Editor from Few-Shot Examples

papers (10)

SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer

Stable-Hair: Real-World Hair Transfer via Diffusion Model

Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks

Image Watermarks are Removable using Controllable Regeneration from Clean Noise

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

FonTS: Text Rendering With Typography and Style Controls

IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation

DiffSim: Taming Diffusion Models for Evaluating Visual Similarity

ArtEditor: Learning Customized Instructional Image Editor from Few-Shot Examples