Vision encoders alter spectral accessibility non-monotonically across depth with architecture-specific effects from projections and pooling, quantified via a new residual loss against random baselines.
Anti-oversmoothing in deep vision transformers via the fourier domain analysis: From the- ory to practice
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
SeedPolicy introduces self-evolving gated attention to extend the temporal horizon of diffusion policies, yielding 36.8% and 169% relative gains over standard DP on clean and randomized RoboTwin 2.0 tasks.
Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.
citing papers explorer
-
Beyond Compression: Quantifying Spectral Accessibility in Vision Representations
Vision encoders alter spectral accessibility non-monotonically across depth with architecture-specific effects from projections and pooling, quantified via a new residual loss against random baselines.
-
Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging
Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.