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.
Anti-oversmoothing in deep vision transformers via the fourier domain analysis: From theory to practice
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
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
-
SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation
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.
-
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.