Lasting Effects of Abstract Pretraining Beyond Perplexity
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/zlshinnick/procedural-pretraining
Terminology
Sources
- Neural Networks Learn Statistics of Increasing Complexity
- Universal pre-training by iterated random computation
- Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility
- TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
- Meta-Learning Neural Mechanisms rather than Bayesian Priors
- Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
- Training Compute-Optimal Large Language Models
- Training Language Models via Neural Cellular Automata
- Modeling rapid language learning by distilling Bayesian priors into artificial neural networks
- Injecting structural hints: Using language models to study inductive biases in language learning
- Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models
- Transformers converge to invariant algorithmic cores
- Structural priors for data-efficient language learning
- Perplexity Cannot Always Tell Right from Wrong
- Intelligence at the Edge of Chaos
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