Daneul Kim

carpedkm's activity

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

upvoted 2 papers 42 minutes ago

Story Visualization by Online Text Augmentation with Context Memory

Paper • 2308.07575 • Published Aug 15, 2023 • 1

Pick-or-Mix: Dynamic Channel Sampling for ConvNets

Paper • 2406.10935 • Published Jun 16, 2024 • 1

liked a dataset 42 minutes ago

UCSC-VLAA/HQ-Edit

Viewer • Updated Apr 17, 2024 • 1.64k • 2.61k • 29

authored a paper about 19 hours ago

Improving Editability in Image Generation with Layer-wise Memory

Paper • 2505.01079 • Published 4 days ago • 18

upvoted a paper about 22 hours ago

Improving Editability in Image Generation with Layer-wise Memory

Paper • 2505.01079 • Published 4 days ago • 18

commented a paper about 22 hours ago

Improving Editability in Image Generation with Layer-wise Memory

Paper • 2505.01079 • Published 4 days ago • 18 •

1

upvoted a paper 7 days ago

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models

Paper • 2504.17789 • Published 11 days ago • 23

authored a paper 8 days ago

Story Visualization by Online Text Augmentation with Context Memory

Paper • 2308.07575 • Published Aug 15, 2023 • 1

upvoted 3 papers 8 days ago

Towards Understanding Camera Motions in Any Video

Paper • 2504.15376 • Published 14 days ago • 154

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published 10 days ago • 41

Subject-driven Video Generation via Disentangled Identity and Motion

Paper • 2504.17816 • Published 13 days ago • 11

commented a paper 8 days ago

Subject-driven Video Generation via Disentangled Identity and Motion

Paper • 2504.17816 • Published 13 days ago • 11 •

2

authored 2 papers 8 days ago

Pick-or-Mix: Dynamic Channel Sampling for ConvNets

Paper • 2406.10935 • Published Jun 16, 2024 • 1

Subject-driven Video Generation via Disentangled Identity and Motion

Paper • 2504.17816 • Published 13 days ago • 11

liked a dataset 5 months ago

laion/relaion2B-en-research-safe

Viewer • Updated Jul 2, 2024 • 2.1B • 2.33k • 196

liked 2 Spaces about 1 year ago

Sleeping

137

137

Multidiffusion Spatial Controls

✏

Running

544

544

Vision Arena (Testing VLMs side-by-side)

🖼

Analyze images to detect and label objects

liked a model about 1 year ago

stabilityai/stable-code-3b

Text Generation • Updated Jul 10, 2024 • 4.88k • 642