Picture for Song Wen

Song Wen

Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models

Add code
May 31, 2024
Viaarxiv icon

Implicit In-context Learning

Add code
May 23, 2024
Viaarxiv icon

Improving Compositional Text-to-image Generation with Large Vision-Language Models

Oct 10, 2023
Figure 1 for Improving Compositional Text-to-image Generation with Large Vision-Language Models
Figure 2 for Improving Compositional Text-to-image Generation with Large Vision-Language Models
Figure 3 for Improving Compositional Text-to-image Generation with Large Vision-Language Models
Figure 4 for Improving Compositional Text-to-image Generation with Large Vision-Language Models
Viaarxiv icon

ImageBind-LLM: Multi-modality Instruction Tuning

Add code
Sep 11, 2023
Figure 1 for ImageBind-LLM: Multi-modality Instruction Tuning
Figure 2 for ImageBind-LLM: Multi-modality Instruction Tuning
Figure 3 for ImageBind-LLM: Multi-modality Instruction Tuning
Figure 4 for ImageBind-LLM: Multi-modality Instruction Tuning
Viaarxiv icon

Improving Tuning-Free Real Image Editing with Proximal Guidance

Add code
Jun 29, 2023
Figure 1 for Improving Tuning-Free Real Image Editing with Proximal Guidance
Figure 2 for Improving Tuning-Free Real Image Editing with Proximal Guidance
Figure 3 for Improving Tuning-Free Real Image Editing with Proximal Guidance
Figure 4 for Improving Tuning-Free Real Image Editing with Proximal Guidance
Viaarxiv icon

Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks

Add code
Mar 07, 2023
Figure 1 for Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Figure 2 for Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Figure 3 for Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Figure 4 for Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Viaarxiv icon

Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification

May 20, 2021
Figure 1 for Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
Figure 2 for Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
Figure 3 for Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
Figure 4 for Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
Viaarxiv icon

Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty

Jan 12, 2021
Figure 1 for Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
Figure 2 for Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
Figure 3 for Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
Figure 4 for Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
Viaarxiv icon

Crowd Counting on Images with Scale Variation and Isolated Clusters

Sep 09, 2019
Figure 1 for Crowd Counting on Images with Scale Variation and Isolated Clusters
Figure 2 for Crowd Counting on Images with Scale Variation and Isolated Clusters
Figure 3 for Crowd Counting on Images with Scale Variation and Isolated Clusters
Figure 4 for Crowd Counting on Images with Scale Variation and Isolated Clusters
Viaarxiv icon