Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Uncovering the Latent Potential of Deep Intermediate Representations
Arnesh Batra, Arush Gumber, Aniket Khandelwal +2
Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric…
cs.LG2025
SocialDF: Benchmark Dataset and Detection Model for Mitigating Harmful Deepfake Content on Social Media Platforms
Arnesh Batra, Anushk Kumar, Jashn Khemani +3
The rapid advancement of deep generative models has significantly improved the realism of synthetic media, presenting both opportunities and security challenges. While deepfake tec…