Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
The free-energy principle: a unified brain theory?Nature reviews neuroscience, 11(2):127–138
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
DynoSys offers a unified dynamic systems model integrating genetic, environmental, and neurobiological signals to analyze longitudinal behavioral phenotypes in adolescents via harmonized representations and survival or state-space modeling.
citing papers explorer
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
-
Axiomatizing Neural Networks via Pursuit of Subspaces
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
-
DynoSys: A Dynamic Systems Framework for Multimodal Integration of Genetic, Environmental, and Neurobiological Signals
DynoSys offers a unified dynamic systems model integrating genetic, environmental, and neurobiological signals to analyze longitudinal behavioral phenotypes in adolescents via harmonized representations and survival or state-space modeling.
- CogniFold: Always-On Proactive Memory via Cognitive Folding
- Dynamic Representational Synchrony through Collective Predictive Coding: A Computational Model of Parent-Infant Homeostatic Co-Regulation