Neural Dynamics as the Composition of Quantized Units
cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/SakanaAI/quanta
Terminology
Sources
- Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
- Scaling Laws for Neural Language Models
- What do Language Models Learn and When? The Implicit Curriculum Hypothesis
- Physics of Skill Learning
- Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
- There Will Be a Scientific Theory of Deep Learning
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks