Replay in the Silent Degrees of Freedom: Continual Learning Without an Offline Phase
cs.LG, cs.NE, stat.ML
Submitted: 2026-09-09
Updated: 2026-10-03
Comments: Accepted into NeurIPS 2026 Workshop on Continual Learning in the Era of Foundation Models and Embodied Agents
Code: https://github.com/Hanny658/IaC-Replay-in-SDF
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks
- Continual Learning via Neural Pruning
- Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
- Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks
- Continual learning benefits from multiple sleep mechanisms: NREM, REM, and Synaptic Downscaling
- Algorithmic insights on continual learning from fruit flies
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks