Sangmin Han

Sang-Min-i's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 months ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published Nov 12, 2025 • 127

upvoted 3 papers 5 months ago

TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

Paper • 2508.04324 • Published Aug 6, 2025 • 11

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation

Paper • 2508.08248 • Published Aug 11, 2025 • 27

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4, 2025 • 272

upvoted an article 6 months ago

view article

Article

Extending *Transformer layers as Painters* to DiT's

• 

Aug 31, 2024

•

16

upvoted a paper 6 months ago

4KAgent: Agentic Any Image to 4K Super-Resolution

Paper • 2507.07105 • Published Jul 9, 2025 • 106

upvoted 5 papers 9 months ago

Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

Paper • 2505.17561 • Published May 23, 2025 • 31

IP-Composer: Semantic Composition of Visual Concepts

Paper • 2502.13951 • Published Feb 19, 2025 • 2

InstanceGen: Image Generation with Instance-level Instructions

Paper • 2505.05678 • Published May 8, 2025 • 7

LightLab: Controlling Light Sources in Images with Diffusion Models

Paper • 2505.09608 • Published May 14, 2025 • 37

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

Paper • 2505.08787 • Published May 13, 2025 • 14

upvoted a paper 10 months ago

CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy

Paper • 2504.07959 • Published Apr 10, 2025 • 10

upvoted 3 papers 11 months ago

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models

Paper • 2503.18446 • Published Mar 24, 2025 • 12

Reangle-A-Video: 4D Video Generation as Video-to-Video Translation

Paper • 2503.09151 • Published Mar 12, 2025 • 32

Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation

Paper • 2501.03059 • Published Jan 6, 2025 • 22

upvoted 5 papers 12 months ago

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

Paper • 2501.01427 • Published Jan 2, 2025 • 53

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Paper • 2502.02492 • Published Feb 4, 2025 • 66

Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening

Paper • 2502.12146 • Published Feb 17, 2025 • 16

Goku: Flow Based Video Generative Foundation Models

Paper • 2502.04896 • Published Feb 7, 2025 • 106

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Paper • 2502.08590 • Published Feb 12, 2025 • 42