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.
We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This problem is closely related to in-context learning and...
arXiv:2601.03199v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. Existing In-Context...
arXiv:2609.38149v1 Announce Type: new Abstract: Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for informa...
Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adjacent token spans are highly predictable or freque...
Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly understood. We consider suc...
arXiv:2607. 22646v1 Announce Type: new Abstract: Large language models (LLMs) display a striking ability to predict next observations from Hidden Markov Models (HMMs) via in-context learning (ICL), but the algorithm underlying this capability remains undetermined: prior work has proposed several candidates without consensus, and none has been grounded in the model's internal activations.
The paper presents practical training recipes for looped language models, showing that a compute‑efficient pipeline can reduce the training budget from 7.7 T tokens to 310 B tokens while maintaining strong reasoning performance. In controlled experiments, a 1.4 B LoopLM outperforms a parameter‑matched dense model on 12 benchmarks, achieving significant gains on GSM8K, MATH, and DROP, and approaches a 3.9 B dense model at matched inference compute. The authors also provide a minimal recipe to convert pretrained dense models into looped ones, demonstrating improvements on Qwen3‑1.7B‑Base across multiple data regimes.
arXiv:2609.27233v1 Announce Type: new Abstract: Transformer language models process sequences token by token in an autoregressive manner, making growing contexts increasingly expensive. Yet many adja...
Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in predictable token counts, retrievals stop after a few sentences, retractions extend responses by measurable amounts. We ask whether the model carries an internal estimate of how much response remains.
arXiv:2607. 05316v1 Announce Type: cross Abstract: Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in predictable token counts, retrievals stop after a few sentences, retractions extend responses by measurable amounts.
arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requi...
arXiv:2609.17376v1 Announce Type: new Abstract: Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that supp...