Papers › Looped Transformers for Length Generalization

Looped Transformers for Length Generalization

24 Sep 2024arXiv:2409.15647archive 2025-07-28

Ying Fan, Yilun Du, Kannan Ramchandran, Kangwook Lee

Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While these Transformers generalize well on unseen inputs of the same length, they struggle with length generalization, i.e., handling inputs of unseen lengths. In this work, we demonstrate that looped Transformers with an adaptive number of steps significantly improve length generalization. We focus on tasks with a known iterative solution, involving multiple iterations of a RASP-L operation - a length-generalizable operation that can be expressed by a finite-sized Transformer. We train looped Transformers using our proposed learning algorithm and observe that they learn highly length-generalizable solutions for various tasks.

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 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 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: official repository: 17 samples from 1 repository, 14 ran (10 with no instrument failure; 4 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.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

uw-madison-lee-lab/looped-tf officialmentioned in papermentioned on GitHubjaxSyntology: 17 samples, 14 ran (4 instrument-failed) · 3 unverified 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.

Code Syntology ran Syntology

17 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
4ran
3unverified

Licence: 17 of the 17 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 uw-madison-lee-lab/looped-tf. “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.

uw-madison-lee-lab/looped-tf official repository 17 samples, 14 ran (4 instrument-failed) · 3 unverified
build_general_model src/models.py ran no licence file found · pointer only · b87d86c9476163f8 · report fixture: signature conf:MockConfig/0/?, y_dim:int/0/int · returned GeneralTransformerModel · level recorded 2026-09-24
check_number_comma in 14 papers src/transformers/convert_slow_tokenizer.py ran · violated contract no licence file found · pointer only · a727df5fd2f5599a · report fixture: signature piece:str/0/str · returned bool · level recorded 2026-09-24
convert_to_one_hot in 10 papers src/utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 2b0656642339e6c3 · report fixture: signature int_matrix:ndarray/2/int · returned ndarray · level recorded 2026-09-24
decimal_to_binary src/generate_training_data.py ran · honoured contract no licence file found · pointer only · 8093f1fb3f100aa2 · report fixture: signature decimal_num:int/0/int · returned Tensor · level recorded 2026-09-24
ensure_valid_input in 15 papers src/transformers/convert_graph_to_onnx.py ran · our draft was wrong no licence file found · pointer only · d770e1dd1d799a47 · report fixture: signature model:callable/0/?, tokens:dict/0/?, input_names:list/1/str · returned tuple · level recorded 2026-09-24
exact_match_accuracy src/utils.py ran · our draft was wrong no licence file found · pointer only · 13826a704319bc71 · report fixture: signature predicted_sequences:Tensor/2/int, target_sequences:Tensor/2/int · returned float64 · level recorded 2026-09-24
gelu_fast in 39 papers src/transformers/activations_tf.py ran · honoured contract fingerprinted no licence file found · pointer only · 37a5eed2dbd663ca · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
generate_identified_filename in 15 papers src/transformers/convert_graph_to_onnx.py ran · our draft was wrong no licence file found · pointer only · 7efe3db5c9e2f94d · report fixture: signature filename:PosixPath/0/?, identifier:str/0/str · returned PosixPath · level recorded 2026-09-24
generate_prompt_matrix_parity src/generate_training_data.py ran no licence file found · pointer only · e8bfa1d05b93d145 · report fixture: signature b:int/0/int, max_len:int/0/int, min_num_digits:int/0/int, max_num_digits:int/0/int · returned tuple · level recorded 2026-09-24
generate_prompt_matrix_sum_reverse src/generate_training_data.py ran no licence file found · pointer only · c4d0ba9418abbc31 · report fixture: signature b:int/0/int, max_len:int/0/int, min_num_digits:int/0/int, max_num_digits:int/0/int · returned tuple · level recorded 2026-09-24
get_final_var in 9 papers src/curriculum.py ran no licence file found · pointer only · 3c24ac252fef0868 · report fixture: signature init_var:float/0/float, total_steps:int/0/int, inc:float/0/float, n_steps:int/0/int, lim:float/0/float · returned float · level recorded 2026-09-25
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
src/transformers/activations_tf.py ran · honoured contract no licence file found · pointer only · cc8c8c3ebf0c343f · report fixture: signature x:ndarray/2/float · returned EagerTensor · level recorded 2026-09-26
one_hot_to_int src/utils.py ran · honoured contract fingerprinted no licence file found · pointer only · e427721d61f5277d · report fixture: signature one_hot_matrix:ndarray/2/float · returned ndarray · level recorded 2026-09-24
quick_gelu in 43 papers src/transformers/activations_tf.py ran · honoured contract fingerprinted no licence file found · pointer only · e2d56cb91f999bef · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
convert_slow_tokenizer in 14 papers src/transformers/convert_slow_tokenizer.py unverified no licence file found · pointer only · 11edc6c69e396f6c · report
get_configuration_file in 13 papers src/transformers/configuration_utils.py unverified no licence file found · pointer only · dd3166a87bc972ff · report
infer_shapes in 15 papers src/transformers/convert_graph_to_onnx.py unverified no licence file found · pointer only · 3449d7d975edfb89 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFocusLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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