Picture for Songhua Liu

Songhua Liu

OminiControl: Minimal and Universal Control for Diffusion Transformer

Add code
Nov 25, 2024
Viaarxiv icon

Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching

Add code
Oct 10, 2024
Viaarxiv icon

LinFusion: 1 GPU, 1 Minute, 16K Image

Add code
Sep 03, 2024
Viaarxiv icon

Heavy Labels Out! Dataset Distillation with Label Space Lightening

Add code
Aug 15, 2024
Figure 1 for Heavy Labels Out! Dataset Distillation with Label Space Lightening
Figure 2 for Heavy Labels Out! Dataset Distillation with Label Space Lightening
Figure 3 for Heavy Labels Out! Dataset Distillation with Label Space Lightening
Figure 4 for Heavy Labels Out! Dataset Distillation with Label Space Lightening
Viaarxiv icon

Video-Infinity: Distributed Long Video Generation

Add code
Jun 24, 2024
Figure 1 for Video-Infinity: Distributed Long Video Generation
Figure 2 for Video-Infinity: Distributed Long Video Generation
Figure 3 for Video-Infinity: Distributed Long Video Generation
Figure 4 for Video-Infinity: Distributed Long Video Generation
Viaarxiv icon

StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization

Add code
Jun 01, 2024
Figure 1 for StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
Figure 2 for StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
Figure 3 for StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
Figure 4 for StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
Viaarxiv icon

Distilled Datamodel with Reverse Gradient Matching

Add code
Apr 22, 2024
Viaarxiv icon

MindBridge: A Cross-Subject Brain Decoding Framework

Add code
Apr 11, 2024
Viaarxiv icon

Mutual-modality Adversarial Attack with Semantic Perturbation

Add code
Dec 20, 2023
Viaarxiv icon

SG-Former: Self-guided Transformer with Evolving Token Reallocation

Add code
Aug 23, 2023
Viaarxiv icon