Jiaming Han

csuhan's activity

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

authored a paper 2 days ago

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Paper • 2506.18898 • Published 2 days ago • 23

updated a collection 2 days ago

Tar

Collection

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations • 4 items • Updated 2 days ago

upvoted a paper 2 days ago

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Paper • 2506.18898 • Published 2 days ago • 23

commented a paper 2 days ago

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Paper • 2506.18898 • Published 2 days ago • 23 •

1

updated a Space 2 days ago

Running on A10G

59

59

Tar

🚀

Unified MLLM with Text-Aligned Representations

published a dataset 6 days ago

csuhan/ImageNet1K-T2I-QwenVL-FLUX

Viewer • Updated 14 days ago • 1.28M • 398

updated a collection 6 days ago

Tar

Collection

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations • 4 items • Updated 2 days ago

updated a collection 7 days ago

Tar

Collection

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations • 4 items • Updated 2 days ago

updated a dataset 12 days ago

csuhan/midjourney-prompts-FLUX

Viewer • Updated 12 days ago • 18.2M • 380

published a dataset 12 days ago

csuhan/midjourney-prompts-FLUX

Viewer • Updated 12 days ago • 18.2M • 380

upvoted a paper 14 days ago

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Paper • 2506.09350 • Published 15 days ago • 48

updated a dataset 14 days ago

csuhan/LLaVA-SFT-665K

Viewer • Updated 14 days ago • 615k • 462

published a dataset 14 days ago

csuhan/LLaVA-SFT-665K

Viewer • Updated 14 days ago • 615k • 462

updated a dataset 14 days ago

csuhan/ImageNet1K-T2I-QwenVL-FLUX

Viewer • Updated 14 days ago • 1.28M • 398

upvoted a paper 20 days ago

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Paper • 2506.05301 • Published 20 days ago • 55

liked 3 datasets about 2 months ago

jackyhate/text-to-image-2M

Viewer • Updated Sep 22, 2024 • 649k • 7.87k • 108

BAAI/Infinity-MM

Updated Dec 13, 2024 • 24.3k • 104

OpenGVLab/ShareGPT-4o

Viewer • Updated Aug 17, 2024 • 59.4k • 3.6k • 174

liked a dataset 2 months ago

UCSC-VLAA/Complex-Edit

Viewer • Updated Apr 20 • 1.06k • 224 • 4