The paper presents quantitative generalization bounds for fixed‑precision transformer models, addressing both in‑distribution statistical generalization and length generalization. It derives guarantees based on model parameters, quantization space, and alphabet size, and shows how training length and sample size trade off, with longer training being exponentially more efficient. Experiments confirm the theoretical predictions.
arXiv:2604.13082v3 Announce Type: replace-cross Abstract: Large language models today still make mistakes on multi-digit arithmetic when they do not have tools, and part of the reason is how numbers...
arXiv:2609.08851v1 Announce Type: new Abstract: Recent advancements in transformer length generalization theory enable us to reliably predict when a transformer can learn to solve a task. In particul...
arXiv:2603. 02238v2 Announce Type: replace Abstract: Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data.
arXiv:2610. 34553v1 Announce Type: new Abstract: How efficiently can transformers store factual knowledge?
arXiv:2512. 22088v3 Announce Type: replace-cross Abstract: The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources.
arXiv:2604. 25800v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing completeness.
arXiv:2610.26974v1 Announce Type: new Abstract: We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depend...
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
The paper investigates how to effectively pre‑train language models when the data budget is limited but compute is plentiful. It shows that increasing model size only improves performance up to an optimal point, after which overfitting degrades generalization, and that this optimal size varies with both the data budget and downstream tasks. To overcome the inefficiencies of standard Transformers in this regime, the authors propose recursive Transformers that reuse a shared block across depth and employ factorized embeddings, achieving better results than standard models on 10M–100M word pre‑training budgets and competitive performance with BabyLM Challenge 2025 winners.
arXiv:2607. 17624v1 Announce Type: new Abstract: Transformers are remarkably versatile and their design is largely consistent across a variety of applications.
arXiv:2606. 29256v1 Announce Type: cross Abstract: In recent years, models based on the Transformer architecture have seen widespread applications and have become one of the core tools in the field of deep learning.
The paper addresses the challenge of selecting demonstrations for long-context language model queries, where transformer inference costs grow quadratically with sequence length. It proposes two algorithms that distill transformer behavior into state space models (SSMs) with linear inference time, partitioning transformer layers into groups and estimating separate SSMs for each. The distilled SSMs achieve less than 0.7% approximation error, and in downstream tasks they reduce FLOPs by 14.2× while improving accuracy by 6.48% compared to baseline methods.