arXiv Machine Learning
Jun 5
The Topological Trouble With Transformers
arXiv:2604. 17121v3 Announce Type: replace Abstract: Transformers encode structure in sequences via an expanding contextual history.
Beyond Episodic AI: Cognitive Field Networks for Biologically Inspired Persistent Cognition
Related stories
arXiv AI
Jun 19
CogniFold: Always-On Proactive Memory via Cognitive Folding
arXiv:2605. 13438v3 Announce Type: replace Abstract: Existing agent memory remains predominantly reactive and retrieval-based, lacking the capacity to autonomously organize experience into persistent cognitive structure.
arXiv AI
Sep 10
Memory in Deep Time-Series Models
arXiv:2609.06006v1 Announce Type: cross Abstract: Deep learning for time series has progressed through successive architectural paradigms, from recurrent networks and transformers to structured state...
arXiv Machine Learning
Jul 15
Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle
arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.
arXiv Machine Learning
Aug 18
Metaplasticity as adaptive gradient preconditioning for incremental learning
arXiv:2608. 14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses.
arXiv AI
6d ago
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
Jun 5
Unraveling the Hidden Dynamical Structure in Recurrent Neural Policies
arXiv:2602. 01196v2 Announce Type: replace Abstract: Recurrent neural policies are widely used in partially observable control and meta-RL tasks.
arXiv AI
Sep 16
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
arXiv:2609.16053v1 Announce Type: cross Abstract: Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new inf...
arXiv Machine Learning
Sep 1
Reproducible macroscopic dynamics in a closed-loop human-AI learning system
arXiv:2608.30946v1 Announce Type: new Abstract: Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adapt...
arXiv AI
Sep 7
MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
MePo++ is a post‑training framework designed for general continual learning (GCL) that unifies representation refinement and reconciliation. It introduces MetaPrep, which enhances representation plasticity via unsupervised meta‑refinement on pseudo continual sequences, and StreamAlign, which maintains stability by reconciling online features with a stable pretrained geometry. Experiments across various pretrained models, datasets, and continual learning baselines show that MePo++ consistently improves performance in PTM‑based GCL.
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
Jun 24
Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping
arXiv:2606. 24396v1 Announce Type: new Abstract: Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{ramsauer2020hopfield, wu2024attention}.