Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees

arXiv:2608.30072 · stat.ML, cs.LG, math.ST, stat.TH · Submitted 2026-08-30 · Read on arXiv

stat.ML, cs.LG, math.ST, stat.TH

Submitted: 2026-08-30

Updated: 2026-08-30

Terminology

• Embeddings — 45× in this paper · explained in 2 episodes
• Consistency — 27× in this paper · explained in 3 episodes
• Self-consistency — 25× in this paper · explained in 2 episodes
• Transformer — 18× in this paper · explained in 2 episodes
• Clustering — 16× in this paper · explained in 2 episodes
• Linear probe — 11× in this paper · explained in 2 episodes
• Regret — 11× in this paper · explained in 3 episodes
• Representation Learning — 11× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Reward Function — 7× in this paper · explained in 2 episodes
• Downstream Tasks — 4× in this paper · explained in 2 episodes
• Spectral clustering — 4× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Self-Supervised Learning — 2× in this paper · explained in 8 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Contextual Bandits — 1× in this paper · explained in 3 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Wasserstein Distance — 1× in this paper · explained in 4 episodes

Sources

• On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey