Subliminal learning occurs via compatible auxiliary and class output heads on task-unrelated inputs, even with random hidden layers or architecture changes, with theory and upper bounds on failure.
Delving deep into rectifiers: Surpassing human-level performance on imagenet classification
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
LoMETab is a rank-r generalization of multiplicative implicit ensembles that strictly enlarges the hypothesis class for r >= 2 and supplies tunable control over predictive diversity via adapter rank and initialization scale.
In linear recurrent models, infinite-width signal propagation remains accurate only for depths t much smaller than sqrt(width n), with a critical regime at t ~ c sqrt(n) where finite-width effects emerge and dominate for larger t.
citing papers explorer
-
Learning Through Noise: Why Subliminal Learning Works and When It Fails
Subliminal learning occurs via compatible auxiliary and class output heads on task-unrelated inputs, even with random hidden layers or architecture changes, with theory and upper bounds on failure.
-
LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning
LoMETab is a rank-r generalization of multiplicative implicit ensembles that strictly enlarges the hypothesis class for r >= 2 and supplies tunable control over predictive diversity via adapter rank and initialization scale.
-
How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
In linear recurrent models, infinite-width signal propagation remains accurate only for depths t much smaller than sqrt(width n), with a critical regime at t ~ c sqrt(n) where finite-width effects emerge and dominate for larger t.