Andy Yermakov

yermandy's activity

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

New activity in WenhaoWang/ScaleDF 10 days ago

Videos

6

#2 opened about 1 month ago by

yermandy

liked a Space about 1 month ago

Running

611

AI Deadlines

⚡

611

Find and manage important project deadlines and milestones

liked 2 datasets about 2 months ago

saberzl/So-Fake-OOD

Viewer • Updated Oct 3, 2025 • 199k • 2.41k • 7

saberzl/So-Fake-Set

Viewer • Updated Oct 29, 2025 • 2.23M • 7.58k • 8

authored a paper about 2 months ago

Deepfake Detection that Generalizes Across Benchmarks

Paper • 2508.06248 • Published Aug 8, 2025

updated 3 models about 2 months ago

yermandy/GenD_PE_L

Image Classification • 0.3B • Updated Nov 13, 2025 • 784 • 1

yermandy/GenD_CLIP_L_14

Image Classification • 0.3B • Updated Nov 13, 2025 • 1.1k

yermandy/GenD_DINOv3_L

Image Classification • 0.3B • Updated Nov 13, 2025 • 561

updated a collection about 2 months ago

GenD

Collection

Models for the WACV 2026 paper: "Deepfake Detection that Generalizes Across Benchmarks" • 4 items • Updated Nov 14, 2025

published 2 models about 2 months ago

yermandy/GenD_DINOv3_L

Image Classification • 0.3B • Updated Nov 13, 2025 • 561

yermandy/GenD_PE_L

Image Classification • 0.3B • Updated Nov 13, 2025 • 784 • 1

published a model 2 months ago

yermandy/GenD_CLIP_L_14

Image Classification • 0.3B • Updated Nov 13, 2025 • 1.1k

liked a Space 2 months ago

Running on CPU Upgrade

Featured

2.83k

The Smol Training Playbook

📚

2.83k

The secrets to building world-class LLMs

New activity in nvidia/C-RADIOv3-L 3 months ago

Cannot load the model

➕ 1

1

#7 opened 3 months ago by

yermandy

liked 3 Spaces 5 months ago

Running

Featured

152

DINOv3 Web

🦖

152

Visualize rich, dense image features locally in your browser

Running on CPU Upgrade

Featured

919

TTS Arena V2

🏆

919

Vote on the latest TTS models!

Running on CPU Upgrade

Featured

1.19k

Open ASR Leaderboard

🏆

1.19k

View and request speech models benchmark data