Andy Yermakov

yermandy

8 3 15

https://yermandy.github.io/

yermandy

AI & ML interests

Computer Vision and Machine Learning

Recent Activity

new activity 4 days ago

JamalLee/Omni-Fake-OOD:ACTalker is truncated having 400 instead of 1000 videos

upvoted a collection 6 days ago

TimesFM Release

upvoted an article 20 days ago

What We Learned by Reproducing 2,200 papers from ICML

View all activity

Organizations

None yet

liked a dataset 7 months ago

luchaoqi/TalkingHeadBench

Viewer • Updated Apr 6 • 2.92k • 1.02k • 11

liked a Space 9 months ago

AI Deadlines

⚡

780

Track upcoming AI conference deadlines

liked 2 datasets 10 months ago

saberzl/So-Fake-OOD

Viewer • Updated Aug 3 • 91.4k • 1.17k • 9

saberzl/So-Fake-Set

Viewer • Updated Oct 29, 2025 • 2.23M • 3.27k • 11

liked a Space 10 months ago

The Smol Training Playbook

📚

3.29k

The secrets to building world-class LLMs

liked 4 Spaces about 1 year ago

DINOv3 Web

🦖

160

Visualize rich, dense image features locally in your browser

TTS Arena V2

🗣

973

Compare two text-to-speech voices and vote for the better

Open ASR Leaderboard

🏆

1.45k

Explore ASR model performance across datasets

Kokoro TTS

❤

3.45k

Upgraded to v1.0!

liked a model about 1 year ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 11.5M • • 6.82k

liked 2 datasets about 1 year ago

cambrain/DigiFakeAV

Updated Mar 12 • 2.05k • 4

sywang/CNNDetection

Updated Jul 26, 2024 • 6.53k • 6

liked a model over 1 year ago

laion/CLIP-ViT-g-14-laion2B-s12B-b42K

1B • Updated Feb 23, 2024 • 12.8k • 44

liked a Space over 2 years ago

Grounded Segment Anything

📚

395

liked a model almost 3 years ago

stabilityai/sdxl-turbo

Text-to-Image • 3B • Updated Jul 10, 2024 • 716k • 2.63k