InsideSSL analyzes self-supervised speech models layer-by-layer using entropy, curvature, robustness metrics, and a cross-layer Generative Compatibility Matrix, finding that training objectives induce distinct compression and geometric regimes that correlate with downstream task performance.
Large language models implic- itly learn to straighten neural sentence trajectories to construct a predictive representation of natural language
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective
InsideSSL analyzes self-supervised speech models layer-by-layer using entropy, curvature, robustness metrics, and a cross-layer Generative Compatibility Matrix, finding that training objectives induce distinct compression and geometric regimes that correlate with downstream task performance.