Methods › Natural Language Processing › Autoregressive Transformers › Transformer-XL
Transformer-XL
Introduced by Zihang Dai et al. in Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Transformer-XL (meaning extra long) is a Transformer architecture that introduces the notion of recurrence to the deep self-attention network. Instead of computing the hidden states from scratch for each new segment, Transformer-XL reuses the hidden states obtained in previous segments. The reused hidden states serve as memory for the current segment, which builds up a recurrent connection between the segments. As a result, modeling very long-term dependency becomes possible because information can be propagated through the recurrent connections. As an additional contribution, the Transformer-XL uses a new relative positional encoding formulation that generalizes to attention lengths longer than the one observed during training.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 36 in the graph, strongest link: official). This answer is about arXiv:1901.02860, the paper the archive credits with this method.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Agentic Transformer · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Agentic Transformer') - Waypoint Transformer · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Waypoint Transformer') - Block-State Transformer · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Block-State Transformer') - Bootstrapped Transformer · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Bootstrapped Transformer') - Focused Transformer (FOT) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Focused Transformer (FOT)') - Elastic Decision Transformer · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Elastic Decision Transformer')
Origin paper of this answer, arXiv:1901.02860 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified (of 143 harvested samples) · 43 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 64 · with a code link: 34 · where Syntology ran a sample: 14 (13 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (14 of 64 tagged: 13 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 64 of 64, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
RLBenchNet: The Right Network for the Right Reinforcement Learning Task 21 May 2025 · 1 repository · arXiv:2505.15040
-
A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation 19 Nov 2024 · 0 repositories · arXiv:2411.12157
-
Large Body Language Models 21 Oct 2024 · 0 repositories · arXiv:2410.16533
-
Transformers for Supervised Online Continual Learning 3 Mar 2024 · 0 repositories · arXiv:2403.01554
-
UniMem: Towards a Unified View of Long-Context Large Language Models 5 Feb 2024 · 1 repository · arXiv:2402.03009
-
Memory-efficient Stochastic methods for Memory-based Transformers 14 Nov 2023 · 1 repository · arXiv:2311.08123
-
TRAMS: Training-free Memory Selection for Long-range Language Modeling 24 Oct 2023 · 1 repository · arXiv:2310.15494Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Approximating Two-Layer Feedforward Networks for Efficient Transformers 16 Oct 2023 · 2 repositories · arXiv:2310.10837Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
-
Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents 29 Sep 2023 · 1 repository · arXiv:2309.17207Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Random-Access Infinite Context Length for Transformers 21 Sep 2023 · 1 repository
-
RCMHA: Relative Convolutional Multi-Head Attention for Natural Language Modelling 7 Aug 2023 · 1 repository · arXiv:2308.03429
-
Landmark Attention: Random-Access Infinite Context Length for Transformers 25 May 2023 · 2 repositories · arXiv:2305.16300Syntology official (archive's flag): 1 ran · 11 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified (of 13 harvested samples)
-
Transformer-based World Models Are Happy With 100k Interactions 13 Mar 2023 · 1 repository · arXiv:2303.07109Syntology official (archive's flag): 16 ran · 16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified (of 25 harvested samples)
-
GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music Generation with Transformers 10 Feb 2023 · 0 repositories · arXiv:2302.05393
-
An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generation 31 Jan 2023 · 0 repositories · arXiv:2301.13383
-
Efficient Sparsely Activated Transformers 31 Aug 2022 · 0 repositories · arXiv:2208.14580
-
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models 13 Aug 2022 · 9 repositories · arXiv:2208.06677Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Recurrent Memory Transformer 14 Jul 2022 · 3 repositories · arXiv:2207.06881Syntology official (archive's flag): 3 ran · 6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (of 13 harvested samples) · 2 pointer-only (licence)
-
Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation 24 Apr 2022 · 1 repository · arXiv:2204.11320
-
SinTra: Learning an inspiration model from a single multi-track music segment 21 Apr 2022 · 1 repository · arXiv:2204.09917
-
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models 4 Mar 2022 · 1 repository · arXiv:2203.02094Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
Reconsidering the Past: Optimizing Hidden States in Language Models 16 Dec 2021 · 0 repositories · arXiv:2112.08653
-
A Comparative Study of Transformers on Word Sense Disambiguation 30 Nov 2021 · 0 repositories · arXiv:2111.15417
-
How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN 18 Nov 2021 · 0 repositories · arXiv:2111.09509
-
TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches 8 Nov 2021 · 2 repositories · arXiv:2111.04867
-
Language Modelling via Learning to Rank 13 Oct 2021 · 0 repositories · arXiv:2110.06961
-
Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling 7 Oct 2021 · 1 repository · arXiv:2110.03252
-
FNetAR: Mixing Tokens with Autoregressive Fourier Transforms 22 Jul 2021 · 1 repository · arXiv:2107.10932
-
Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation 11 Jul 2021 · 0 repositories · arXiv:2107.05124
-
ASR Adaptation for E-commerce Chatbots using Cross-Utterance Context and Multi-Task Language Modeling 15 Jun 2021 · 0 repositories · arXiv:2106.09532
-
Adapting Long Context NLM for ASR Rescoring in Conversational Agents 21 Apr 2021 · 0 repositories · arXiv:2104.11070
-
FastMoE: A Fast Mixture-of-Expert Training System 24 Mar 2021 · 3 repositories · arXiv:2103.13262Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
Adaptive Semiparametric Language Models 4 Feb 2021 · 0 repositories · arXiv:2102.02557
-
Mind the Gap: Assessing Temporal Generalization in Neural Language Models 3 Feb 2021 · 1 repository · arXiv:2102.01951
-
Subformer: A Parameter Reduced Transformer 1 Jan 2021 · 0 repositories
-
Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition 1 Dec 2020 · 0 repositories
-
Improving RNN transducer with normalized jointer network 3 Nov 2020 · 0 repositories · arXiv:2011.01576
-
Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset 22 Oct 2020 · 0 repositories · arXiv:2010.11395
-
Transferable Graph Optimizers for ML Compilers 21 Oct 2020 · 0 repositories · arXiv:2010.12438
-
Memformer: A Memory-Augmented Transformer for Sequence Modeling 14 Oct 2020 · 0 repositories · arXiv:2010.06891
-
Pay Attention when Required 9 Sep 2020 · 2 repositories · arXiv:2009.04534
-
The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures 4 Aug 2020 · 2 repositories · arXiv:2008.01307Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples)
-
Language Modelling for Source Code with Transformer-XL 31 Jul 2020 · 1 repository · arXiv:2007.15813
-
Do Transformers Need Deep Long-Range Memory 7 Jul 2020 · 1 repository · arXiv:2007.03356
-
Do Transformers Need Deep Long-Range Memory? 1 Jul 2020 · 0 repositories
-
Probing for Referential Information in Language Models 1 Jul 2020 · 0 repositories
-
Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization 27 Jun 2020 · 0 repositories · arXiv:2006.15435
-
Exploring Transformers for Large-Scale Speech Recognition 19 May 2020 · 0 repositories · arXiv:2005.09684
-
Improving Neural Language Generation with Spectrum Control 1 May 2020 · 0 repositories
-
Segatron: Segment-Aware Transformer for Language Modeling and Understanding 30 Apr 2020 · 1 repository · arXiv:2004.14996
-
Finnish Language Modeling with Deep Transformer Models 14 Mar 2020 · 0 repositories · arXiv:2003.11562
-
Neural Academic Paper Generation 2 Dec 2019 · 1 repository · arXiv:1912.01982
-
DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling 27 Nov 2019 · 1 repository · arXiv:1911.12385
-
Compressive Transformers for Long-Range Sequence Modelling 13 Nov 2019 · 6 repositories · arXiv:1911.05507Syntology 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 11 harvested samples)
-
Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model 23 Oct 2019 · 0 repositories · arXiv:1910.10697
-
Stabilizing Transformers for Reinforcement Learning 13 Oct 2019 · 5 repositories · arXiv:1910.06764Syntology 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
GDP: Generalized Device Placement for Dataflow Graphs 28 Sep 2019 · 0 repositories · arXiv:1910.01578
-
A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning 16 Sep 2019 · 0 repositories · arXiv:1909.06983
-
Ouroboros: On Accelerating Training of Transformer-Based Language Models 14 Sep 2019 · 1 repository · arXiv:1909.06695
-
A Tensorized Transformer for Language Modeling 24 Jun 2019 · 1 repository · arXiv:1906.09777Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
XLNet: Generalized Autoregressive Pretraining for Language Understanding 19 Jun 2019 · 27 repositories · arXiv:1906.08237Syntology official (archive's flag): 1 ran · 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified (of 24 harvested samples) · 4 pointer-only (licence)
-
Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain) 28 May 2019 · 1 repository · arXiv:1905.11833Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
Transformer-XL: Language Modeling with Longer-Term Dependency 1 May 2019 · 0 repositories
-
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context 9 Jan 2019 · 37 repositories · arXiv:1901.02860Syntology official (archive's flag): 8 ran · 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified (of 143 harvested samples) · 43 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 86 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections