Suhwan Choi

MilkClouds's activity

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

updated a Space 10 days ago

Running

5

Visualize Dataset

💻

5

Visualize OWAMcap files

updated a model 11 days ago

open-world-agents/Generalist-IDM-1B

Image-Text-to-Text • 0.9B • Updated 11 days ago • 180 • 2

updated a dataset 13 days ago

open-world-agents/OSTask-demo

Viewer • Updated 12 days ago • 5 • 100

published a dataset 13 days ago

open-world-agents/OSTask-demo

Viewer • Updated 12 days ago • 5 • 100

updated 2 datasets 18 days ago

open-world-agents/D2E-Original

Viewer • Updated 13 days ago • 460 • 2.27k • 2

open-world-agents/D2E-480p

Viewer • Updated 14 days ago • 460 • 3.3k

liked a dataset 25 days ago

HuggingFaceVLA/community_dataset_v3

Updated Dec 10, 2025 • 3.53k • 17

upvoted a paper about 2 months ago

VLA-0: Building State-of-the-Art VLAs with Zero Modification

Paper • 2510.13054 • Published Oct 15, 2025 • 14

commented a paper about 2 months ago

VLA-0: Building State-of-the-Art VLAs with Zero Modification

Paper • 2510.13054 • Published Oct 15, 2025 • 14 •

3

liked a model about 2 months ago

BAAI/Video-XL-2

Video-Text-to-Text • 8B • Updated Jun 6, 2025 • 107 • 55

updated a dataset about 2 months ago

maum-ai/COMMAND

Preview • Updated Dec 3, 2025 • 2.09k • 7

liked a dataset about 2 months ago

maum-ai/COMMAND

Preview • Updated Dec 3, 2025 • 2.09k • 7

New activity in open-world-agents/D2E-480p about 2 months ago

Update README.md

#2 opened about 2 months ago by

MilkClouds

authored 3 papers 3 months ago

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks

Paper • 2505.11881 • Published May 17, 2025 • 4

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7, 2025 • 142

ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models

Paper • 2403.16167 • Published Mar 24, 2024 • 1

upvoted a paper 4 months ago

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7, 2025 • 142

liked 3 datasets 5 months ago

HuggingFaceM4/FineVision

Viewer • Updated Oct 21, 2025 • 24.2M • 118k • 468

HuggingFaceFW/fineweb-edu

Viewer • Updated Jul 11, 2025 • 3.5B • 343k • 916

mlfoundations/dclm-baseline-1.0

Preview • Updated Jul 22, 2024 • 139k • 251