Hugging Face's logo
Mukul Ranjan's picture
🔄 In a Training Loop

Mukul Ranjan

mukul54
7 58 29
P(doom) Rejects the premise
powergirdbat's profile picture Ishitaagarwal's profile picture SondosMB's profile picture
·
https://www.mukul54.github.io

AI & ML interests

Efficiency, Optimization

Recent Activity

reacted to Parveshiiii's post with 🤗 3 days ago
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: https://huggingface.co/Modotte/AIRealNet-Audio
authored a paper 3 days ago
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
upvoted a paper 3 days ago
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
View all activity

Organizations

MBZUAI-LLM's profile picture Mission_CVPR's profile picture Time Blindness's profile picture culture-nlp's profile picture Quant Reasoning's profile picture Diffusion Annotation's profile picture