mlsanityData to 14 Oct 2026

Freely Long-Thinking Transformer (FraiLT)

arXiv 2401.11626 ↗First posted 21 Jan 2024cs.LG cs.CLcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Freely Long-Thinking Transformer (FraiLT) is an improved transformer model designed to enhance processing capabilities without scaling up size. It utilizes a recursive approach, iterating over a subset of layers multiple times, and introduces iteration encodings to maintain awareness across these cycles. Iteration encoding allows FraiLT to achieve the interpretive depth of larger models in a compact form. When evaluated on a synthetic story dataset, FraiLT outperformed larger models, showcasing its ability to deliver high-quality performance while reducing memory demands. This model represents a step forward towards more efficient and accessible language models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 7 of its 9 references that are in the map. First posted on arXiv 21 Jan 2024.

Builds on

7 of 9 references.

References · 7

  1. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  2. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  3. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  4. 2018Universal Transformerscited by 647
  5. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 449
  6. 2022Block-Recurrent Transformerscited by 110
  7. 2016Learning Functions: When Is Deep Better Than Shallowcited by 19

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023MatFormer: Nested Transformer for Elastic Inference
  2. 2025Modality Agnostic Efficient Long Range Encoder
  3. 2024Do Efficient Transformers Really Save Computation?
  4. 2022Efficiently Scaling Transformer Inference
  5. 2023WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
  6. 2025Efficient Adaptive Transformer: An Empirical Study and Reproducible Framework
  7. 2026Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
  8. 2026Transformer-Based Language Models Across Domain Verticals: Architectures, Applications and Critical Assessment