Papers › Generating Sequences With Recurrent Neural Networks

Generating Sequences With Recurrent Neural Networks

4 Aug 2013arXiv:1308.0850archive 2025-07-28

Alex Graves

This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data are discrete) and online handwriting (where the data are real-valued). It is then extended to handwriting synthesis by allowing the network to condition its predictions on a text sequence. The resulting system is able to generate highly realistic cursive handwriting in a wide variety of styles.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 37 code samples harvested from 9 repositories linked to this paper: 31 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 37 samples from 9 repositories, 31 ran (28 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

59 repositories listed; official and paper-mentioned ones first.

Akella17/Handwriting_Synthesis mentioned on GitHubtfSyntology: not harvested report
AnesBenmerzoug/Handwriting-Model mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
AniketBajpai/deep-handwriting-generation mentioned on GitHubpytorchSyntology: not harvested report
AsianZeus/Ooze-Handwritten-Text-Generator mentioned on GitHubtfSyntology: not harvested report
CambridgeIIS/Gesture-Keyboard-Traj-Gen mentioned on GitHubtfSyntology: not harvested report
CongBao/ChatBot mentioned on GitHubSyntology: not harvested report
HEIMaxER/descript-research-test mentioned on GitHubSyntology: not harvested report
Julie260/DeepLearningProject mentioned on GitHubpytorchSyntology: not harvested report
KurtAhn/lyrebird mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Muiiya/research mentioned on GitHubMITSyntology: not harvested report
SamuelNguyen1998/Vietnamese_Handwriting_Recognition mentioned on GitHubtfMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
TengHu/Generating-Sequences-With-Recurrent-Neural-Networks mentioned on GitHubpytorchSyntology: not harvested report
Vrushank264/Handwriting-Generation-using-LSTM mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
YukiDaSlayer316/R-Tutorial mentioned on GitHubSyntology: not harvested report
ZhouYC627/NN_Compression mentioned on GitHubtfSyntology: not harvested report
adbrebs/handwriting mentioned on GitHubSyntology: not harvested report
adrienphilardeau/Descript-Research-Test mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
akhilkumarco007/lyrebird-egg-master mentioned on GitHubtfSyntology: not harvested report
altsoph/paranoid_transformer mentioned on GitHubpytorchSyntology: not harvested report
azfarkhoja305/Handwritten-RNNs mentioned on GitHubpytorchSyntology: not harvested report
badhandas/hw_synthesis mentioned on GitHubpytorchSyntology: not harvested report
canneltigrou/testHandwritting mentioned on GitHubSyntology: not harvested report
ciaua/HandwritingPyTorch mentioned on GitHubpytorchSyntology: not harvested report
cody2007/arcane_fortune mentioned on GitHubNOASSERTIONSyntology: not harvested report
cpmpercussion/keras-mdn-layer mentioned on GitHubtfSyntology: not harvested report
edwin-de-jong/incremental-sequence-learning mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
edwinzhng/handwriting-synthesis mentioned on GitHubtfSyntology: not harvested report
feiwu77777/Handwriting_gen mentioned on GitHubtfSyntology: not harvested report
feiwu77777/Handwriting_generation mentioned on GitHubtfSyntology: not harvested report
greydanus/scribe mentioned on GitHubtfSyntology: not harvested report
grzego/handwriting-generation mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
hardmaru/sketch-rnn-datasets mentioned on GitHubtfSyntology: not harvested report
hardmaru/write-rnn-tensorflow mentioned on GitHubtfSyntology: not harvested report
huyhoang17/Vietnamese_Handwriting_Recognition mentioned on GitHubtfMITSyntology: not harvested report
ikonthomas/Digitize-Handwritten-Texts mentioned on GitHubtfMITSyntology: not harvested report
jolinxql/LSTM mentioned on GitHubSyntology: not harvested report
jparkhill/TensorMol mentioned on GitHubtfGPL-3.0Syntology: not harvested report
karpathy/char-rnn mentioned on GitHubtorchSyntology: not harvested report
karpathy/makemore mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
kedartatwawadi/NN_compression mentioned on GitHubtfMITSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
larspars/word-rnn mentioned on GitHubtorchSyntology: not harvested report
mohitRohatgi/handwritingGenerator mentioned on GitHubSyntology: not harvested report
pnshiralkar/text-to-handwriting mentioned on GitHubtfSyntology: not harvested report
rahul96rajan/text-2-strokes mentioned on GitHubpytorchSyntology: not harvested report
rahulbhalley/Recurrent-Nets-in-Pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
rahulbhalley/rnns-in-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
raymondhs/char-rnn-truecase mentioned on GitHubtorchSyntology: not harvested report
robertknight/textgen mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
rockyyliang/handwrite mentioned on GitHubpytorchSyntology: not harvested report
sjvasquez/handwriting-synthesis mentioned on GitHubtfSyntology: not harvested report
snowkylin/rnn-handwriting-generation mentioned on GitHubtfSyntology: not harvested report
sotelo/scribe mentioned on GitHubSyntology: not harvested report
srikanth-sfu/lyrebird mentioned on GitHubpytorchSyntology: not harvested report
swechhachoudhary/Handwriting-synthesis mentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
szcom/rnnlib mentioned on GitHubGPL-3.0Syntology: not harvested report
vladbataev/handwriting_synthesis mentioned on GitHubpytorchSyntology: not harvested report
yukikongju/R-Tutorial mentioned on GitHubSyntology: not harvested report
gitlab.com/raymondhs/char-rnn-truecase mentioned on GitHubtorchSyntology: not harvested report
sherjilozair/char-rnn-tensorflow tfMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

37 samples harvested: 31 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
24ran
6unverified

Licence: 4 of the 37 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

AnesBenmerzoug/Handwriting-Model community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
filter_line_strokes_and_transcriptions src/handwriting_generator/utils.py ran MIT (permissive) · 316f20cd174551b7 · report fixture: signature line_strokes:dict/0/?, transcriptions:dict/0/?, show_progress:bool/0/bool · returned tuple · level recorded 2026-09-26
load_line_strokes src/handwriting_generator/utils.py ran MIT (permissive) · b15244e710c02e4a · report fixture: signature line_strokes_dir:PosixPath/0/?, show_progress:bool/0/bool · returned dict · level recorded 2026-09-26
load_transcriptions src/handwriting_generator/utils.py ran MIT (permissive) · 1430cb6d9a3f833d · report fixture: signature ascii_dir:PosixPath/0/?, show_progress:bool/0/bool · returned dict · level recorded 2026-09-26
KurtAhn/lyrebird community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
recognize_stroke models/kurt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7f57a4dfdc98e7c2 · report fixture: signature stroke:ndarray/2/float · returned str · level recorded 2026-09-22
SamuelNguyen1998/Vietnamese_Handwriting_Recognition community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
check_eq src/data_utils.py ran MIT (permissive) · e7917e9b49503948 · report fixture: signature img:ndarray/2/int, img2:ndarray/2/int · returned bool · level recorded 2026-09-26
labels_to_text src/utils.py ran MIT (permissive) · 8a9c5ba6da1be290 · report fixture: signature letters:list/1/str, labels:Tensor/1/int · returned str · level recorded 2026-09-26
scale in 38 papers src/data_utils.py ran MIT (permissive) · a43e3c26a372625d · report fixture: signature img:ndarray/2/int, scale_prob:float/0/float, scale_stdv:float/0/float · returned ndarray · level recorded 2026-09-26
text_to_labels src/utils.py ran MIT (permissive) · 0c9fb7323dbd8b8f · report fixture: signature letters:str/0/str, text:str/0/str · returned list · level recorded 2026-09-26
ctc_lambda_func src/loss.py unverified MIT (permissive) · 891407c075760cb4 · report
get_logger in 383 papers src/log.py unverified MIT (permissive) · ce47adec051d5431 · report
Vrushank264/Handwriting-Generation-using-LSTM community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
align in 23 papers utils.py ran fingerprinted MIT (permissive) · 506ea1a5a6aab059 · report fixture: signature coords:ndarray/2/int · returned ndarray · level recorded 2026-09-26
encode_ascii utils.py ran MIT (permissive) · d0ea3aaa2f0cb4d7 · report fixture: signature ascii_str:str/0/str · returned ndarray · level recorded 2026-09-26
mixture_of_bivariate_normal_nll functions.py ran MIT (permissive) · 0858be3fdf9eb3de · report fixture: signature data:Tensor/2/float, log_pi:Tensor/2/float, myu:Tensor/3/float, log_sigma:Tensor/3/float, rho:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-26
mixture_of_bivariate_normal_sample functions.py ran MIT (permissive) · de459a9fb9e0a962 · report fixture: signature log_pi:Tensor/2/float, myu:Tensor/3/float, log_sigma:Tensor/3/float, rho:Tensor/2/float, bias:float/0/float, eps:float/0/float · returned Tensor · level recorded 2026-09-26
preprocess_batch in 6 papers data.py ran MIT (permissive) · c794567624eca063 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-26
skew in 21 papers utils.py ran MIT (permissive) · 57345eef39f87d96 · report fixture: signature coords:ndarray/2/int, degree:int/0/int · returned ndarray · level recorded 2026-09-26
edwin-de-jong/incremental-sequence-learning community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_pi_idx model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 7bb85eb640efb52d · report fixture: signature x:float/0/float, pdf:ndarray/1/float · returned int · level recorded 2026-09-22
grzego/handwriting-generation community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
cumsum in 6 papers generate.py ran · honoured contract fingerprinted MIT (permissive) · 9bafc68792a5453a · report fixture: signature points:ndarray/2/float · returned ndarray · level recorded 2026-09-22
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
generate.py ran · honoured contract MIT (permissive) · b5136c243f64693e · report fixture: signature e:float/0/float, mu1:float/0/float, mu2:float/0/float, std1:float/0/float, std2:float/0/float, rho:float/0/float · returned ndarray · level recorded 2026-09-22
split_strokes generate.py ran · honoured contract MIT (permissive) · 0ff24ae32bac2d32 · report fixture: signature points:list/1/list · returned list · level recorded 2026-09-22
kedartatwawadi/NN_compression community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
entropy_iid src/data_generation_scripts/generate_lagged_fibonacci.py ran fingerprinted MIT (permissive) · 78b673d1702aa8fc · report fixture: signature prob:ndarray/1/float · returned ndarray · level recorded 2026-09-26
vocab_decode misc_code/10_char_rnn_gist.py ran MIT (permissive) · cd578a493dc93a37 · report fixture: signature array:list/1/int, vocab:list/1/str · returned str · level recorded 2026-09-26
vocab_decode misc_code/13_char_rnn_gist.py ran MIT (permissive) · 2d6be2ab08f58d21 · report fixture: signature array:list/1/int, vocab:dict/0/? · returned str · level recorded 2026-09-26
vocab_encode misc_code/10_char_rnn_gist.py ran fingerprinted MIT (permissive) · 3eb3077a0bd2904e · report fixture: signature text:str/0/str, vocab:list/1/str · returned list · level recorded 2026-09-26
create_rnn misc_code/10_char_rnn_gist.py unverified MIT (permissive) · 510351eab5eaed0f · report
create_rnn misc_code/11_char_rnn_gist.py unverified MIT (permissive) · 59b0e285ea9b27a7 · report
create_rnn misc_code/12_char_rnn_gist.py unverified MIT (permissive) · 46bd9f125794535d · report
create_rnn misc_code/15_char_rnn_gist.py unverified MIT (permissive) · c642e923cb957119 · report
robertknight/textgen community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
gen_training_sequences textgen/__main__.py ran · honoured contract no licence file found · pointer only · 232da28e6492c6fb · report fixture: signature text:str/0/str, seq_length:int/0/int, batch_size:int/0/int, vocab:StandInVocab/0/? · returned Tensor · level recorded 2026-09-22
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
textgen/__main__.py ran · our draft was wrong no licence file found · pointer only · bdc663f8a518e964 · report fixture: signature model:callable/0/?, seed_seq:Tensor/2/float, sample_length:int/0/int, device:device/0/?, temperature:float/0/float, vocab:MockVocab/0/? · returned str · level recorded 2026-09-22
swechhachoudhary/Handwriting-synthesis community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
compute_nll_loss utils/model_utils.py ran MIT (permissive) · c89435a714d679dc · report fixture: signature targets:Tensor/3/float, y_hat:Tensor/3/float, mask:Tensor/2/float, M:int/0/int · returned Tensor · level recorded 2026-09-26
data_denormalization utils/data_utils.py ran MIT (permissive) · 8f5f6f10d9df29f1 · report fixture: signature mean:Tensor/1/float, std:Tensor/1/float, data:Tensor/3/float · returned Tensor · level recorded 2026-09-26
path_string_to_stroke app/xml_parser.py ran MIT (permissive) · 453cf42813afb445 · report fixture: signature path:str/0/str, str_len:int/0/int, down_sample:bool/0/bool · returned ndarray · level recorded 2026-09-26
stable_softmax in 7 papers utils/model_utils.py ran fingerprinted MIT (permissive) · 40eb6d67a6e160c6 · report fixture: signature X:Tensor/3/float, dim:int/0/int · returned Tensor · level recorded 2026-09-26
svg_xml_parser app/xml_parser.py ran MIT (permissive) · f84bc9f82b0a9658 · report fixture: signature svg_path:str/0/str · returned list · level recorded 2026-09-26
train_offset_normalization utils/data_utils.py ran fingerprinted MIT (permissive) · e25dad2e1379fe88 · report fixture: signature data:ndarray/3/float · returned tuple · level recorded 2026-09-26
valid_offset_normalization utils/data_utils.py ran MIT (permissive) · 3b394d43bf805dbc · report fixture: signature mean:Tensor/1/float, std:Tensor/1/float, data:Tensor/3/float · returned Tensor · level recorded 2026-09-26

Tasks

Language ModellingText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling enwik8 LSTM (7 layers) Bit per Character (BPC) 1.67 #41 of 42 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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