arXiv AI
Oscillatory Phase Coding Emerges in Adaptive RNNs for Flexible Working Memory
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
4d ago
Clocks all the way down: does sequence-processing AI need endogenous temporal structure?
Mainstream sequence-processing AI is temporally reactive: each update is driven by input and learned state transitions, rather than by an independently evolving internal temporal reference. Biological...
arXiv AI
Sep 25
ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks
The paper introduces ELiSe, a model that leverages cortical network scaffolds and dendritic compartments to learn complex non‑Markovian spatio‑temporal patterns using only local, always‑on, phase‑free synaptic plasticity. It demonstrates the model’s ability to acquire and replay intricate sequences, exemplified by a birdsong learning mock‑up, and shows robustness to external disturbances and flexibility in parameter settings.
arXiv Machine Learning
Oct 15
State Space Models Naturally Produce Time Cell and Oscillatory Behaviors and Scale to Abstract Cognitive Functions
arXiv:2507.13638v4 Announce Type: replace-cross Abstract: A grand challenge in modern neuroscience is bridging the gap between the microscale neural circuits and cognitive functions. While extensive...
arXiv Machine Learning
Jun 25
Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency
arXiv:2604. 07904v2 Announce Type: replace Abstract: Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding.
arXiv AI
Jun 2
SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition
arXiv:2606. 00732v1 Announce Type: new Abstract: Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings.
arXiv Machine Learning
Oct 12
Understanding Mamba-3 Through Oscillatory Dynamics
Mamba-3 incorporates input‑dependent rotations into its recurrent state updates, which the authors interpret as underdamped second‑order dynamics. Experiments show that these oscillatory dynamics outperform non‑oscillatory regimes on state‑tracking tasks and improve long‑context prediction and length generalization in language‑model pretraining. Further interventions confirm that the learned phase is crucial, suggesting that rotation controls how retained information combines with new updates, thereby supporting long‑context processing.