# CoLT5: Faster Long-Range Transformers with Conditional Computation

arXiv: https://arxiv.org/abs/2303.09752 · HTML: https://mlsanity.com/paper/2303.09752/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [Scaling Up Models and Data with textttt5x and textttseqio](https://mlsanity.com/paper/2203.17189/) (2022)
- [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://mlsanity.com/paper/2201.03533/) (2022)
- [ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts](https://mlsanity.com/paper/2110.01799/) (2021)
- [SummScreen: A Dataset for Abstractive Screenplay Summarization](https://mlsanity.com/paper/2104.07091/) (2021)
- [KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://mlsanity.com/paper/2110.04330/) (2021)

## Built on by (most cited first, 30 of 84)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [MoBA: Mixture of Block Attention for Long-Context LLMs](https://mlsanity.com/paper/2502.13189/) (2025)
- [Kimi Linear: An Expressive, Efficient Attention Architecture](https://mlsanity.com/paper/2510.26692/) (2025)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://mlsanity.com/paper/2305.14196/) (2023)
- [Focused Transformer: Contrastive Training for Context Scaling](https://mlsanity.com/paper/2307.03170/) (2023)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [Scaling Transformer to 1M tokens and beyond with RMT](https://mlsanity.com/paper/2304.11062/) (2023)
- [Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference](https://mlsanity.com/paper/2304.04947/) (2023)
- [Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers](https://mlsanity.com/paper/2406.16747/) (2024)
- [Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis](https://mlsanity.com/paper/2405.08944/) (2024)
- [No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models](https://mlsanity.com/paper/2307.06440/) (2023)
- [The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey](https://mlsanity.com/paper/2401.07872/) (2024)
- [DAPE: Data-Adaptive Positional Encoding for Length Extrapolation](https://mlsanity.com/paper/2405.14722/) (2024)
- [Adaptive Layer-skipping in Pre-trained LLMs](https://mlsanity.com/paper/2503.23798/) (2025)
- [System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts](https://mlsanity.com/paper/2505.18962/) (2025)
- [Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation](https://mlsanity.com/paper/2401.16421/) (2024)

## Abstract (arXiv)

Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive -- not only due to quadratic attention complexity but also from applying feedforward and projection layers to every token. However, not all tokens are equally important, especially for longer documents. We propose CoLT5, a long-input Transformer model that builds on this intuition by employing conditional computation, devoting more resources to important tokens in both feedforward and attention layers. We show that CoLT5 achieves stronger performance than LongT5 with much faster training and inference, achieving SOTA on the long-input SCROLLS benchmark. Moreover, CoLT5 can effectively and tractably make use of extremely long inputs, showing strong gains up to 64k input length.