Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
cs.LG, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/paradigms-of-intelligence/rcdl
Sources
- Efficient Attention: Attention with Linear Complexities
- Uncovering mesa-optimization algorithms in Transformers
- ATLAS: Learning to Optimally Memorize the Context at Test Time
- Test-time regression: a unifying framework for designing sequence models with associative memory
- Gaussian Error Linear Units (GELUs)
- Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
- Layer Normalization
- Neural Turing Machines
- Memory Networks
- Cartridges: Lightweight and general-purpose long context representations via self-study
- Progressive Neural Networks
- Growing a Neural Network in Breadth, Depth, and Time
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