Making open-source AI weather forecasting models easy to run
• 44
AI & ML interests
None defined yet.
Recent Activity
Articles
GGUFGuy
published a
model about 22 hours ago
Parveshiiii
posted an update 3 days ago
Post
98
Most NSFW classifiers break the second an image touches the internet.
They look great on pristine benchmarks, but in the wild, every social platform aggressively recompresses, downsamples, and degrades images.
The moment JPEG or WebP compression artifacts show up, confidence collapses and false positives spike.
SafeScan was built to survive actual platform pipelines.
Trained on 34,000 images under almost every major social media compression profile using a Vision Transformer backbone (google/vit-base-patch16-224). Instead of blunt binary filtering, it breaks decisions down across 5 clear categories:
• safe
• drawing
• sexy
• hentai
• porn
The result is a moderation model that actually generalizes to real-world internet feeds instead of fragile, uncompressed datasets.
Open-weight and available on Hugging Face:
Model: Parveshiiii/SafeScan
They look great on pristine benchmarks, but in the wild, every social platform aggressively recompresses, downsamples, and degrades images.
The moment JPEG or WebP compression artifacts show up, confidence collapses and false positives spike.
SafeScan was built to survive actual platform pipelines.
Trained on 34,000 images under almost every major social media compression profile using a Vision Transformer backbone (google/vit-base-patch16-224). Instead of blunt binary filtering, it breaks decisions down across 5 clear categories:
• safe
• drawing
• sexy
• hentai
• porn
The result is a moderation model that actually generalizes to real-world internet feeds instead of fragile, uncompressed datasets.
Open-weight and available on Hugging Face:
Model: Parveshiiii/SafeScan
Hugging Science is DEAD???
➕ 2
38
#2 opened 17 days ago
by 
XBFDI
Karn3003
submitted a
paper to Daily Papers 5 days ago
Parveshiiii
posted an update 5 days ago
Post
3815
Most deepfake audio detectors are quietly cheating.
They don’t really listen to the speech — they just look at how long the embedding vector is. Once they figure that out, accuracy looks great on paper and falls apart in the wild.
AIRealNet-Audio was built to stop that shortcut.
It forces every feature onto the unit hypersphere (twice) so the model can only use direction, not magnitude. Trained on speech from 100+ different TTS and voice-cloning systems, plus real human recordings under heavy compression and noise.
The result is a detector that actually has to learn the artifacts instead of gaming the feature space.
Model: Modotte/AIRealNet-Audio
They don’t really listen to the speech — they just look at how long the embedding vector is. Once they figure that out, accuracy looks great on paper and falls apart in the wild.
AIRealNet-Audio was built to stop that shortcut.
It forces every feature onto the unit hypersphere (twice) so the model can only use direction, not magnitude. Trained on speech from 100+ different TTS and voice-cloning systems, plus real human recordings under heavy compression and noise.
The result is a detector that actually has to learn the artifacts instead of gaming the feature space.
Model: Modotte/AIRealNet-Audio
YOO WHAT?
60
#1 opened 18 days ago
by 
Bc-AI
WAKE UP
11
#5 opened 7 days ago
by GGUFGuy
Hugging Science is DEAD???
➕ 2
38
#2 opened 17 days ago
by XBFDI
YOO WHAT?
60
#1 opened 18 days ago
by Bc-AI
YOO WHAT?
60
#1 opened 18 days ago
by Bc-AI
Hugging Science is DEAD???
➕ 2
38
#2 opened 17 days ago
by XBFDI