4 citations · 6 across the 5 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.SD2026
Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR
Ajinkya Kulkarni, Sandipana Dowerah, Atharva Kulkarni +2
Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We pr…
cs.CL2026
Disentangling Geometry, Performance, and Training in Language Models
Atharva Kulkarni, Jacob Mitchell Springer, Arjun Subramonian +1
Geometric properties of Transformer weights, particularly the unembedding matrix, have been widely useful in language model interpretability research. Yet, their utility for estima…