Papers › Linear Attention for Efficient Bidirectional Sequence Modeling

Linear Attention for Efficient Bidirectional Sequence Modeling

22 Feb 2025arXiv:2502.16249archive 2025-07-28

Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher

Transformers with linear attention enable fast and parallel training. Moreover, they can be formulated as Recurrent Neural Networks (RNNs), for efficient linear-time inference. While extensively evaluated in causal sequence modeling, they have yet to be extended to the bidirectional setting. This work introduces the LION framework, establishing new theoretical foundations for linear transformers in bidirectional sequence modeling. LION constructs a bidirectional RNN equivalent to full Linear Attention. This extends the benefits of linear transformers: parallel training, and efficient inference, into the bidirectional setting. Using LION, we cast three linear transformers to their bidirectional form: LION-LIT, the bidirectional variant corresponding to (Katharopoulos et al., 2020); LION-D, extending RetNet (Sun et al., 2023); and LION-S, a linear transformer with a stable selective mask inspired by selectivity of SSMs (Dao & Gu, 2024). Replacing the attention block with LION (-LIT, -D, -S) achieves performance on bidirectional tasks that approaches that of Transformers and State-Space Models (SSMs), while delivering significant improvements in training speed. Our implementation is available in http://github.com/LIONS-EPFL/LION.

PaperPDFCodeCode Syntology ranMethod as code

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 14 code samples harvested from 1 repository linked to this paper: 14 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 14 ran (4 with no instrument failure; 10 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lions-epfl/lion officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 14 ran (10 instrument-failed) · 0 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.

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

14 samples harvested: 14 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 0 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.

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

Licence: 14 of the 14 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 lions-epfl/lion. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

lions-epfl/lion official repository 14 samples, 14 ran (10 instrument-failed) · 0 unverified
Casual_Mask_Decay_Partial img_classification/lion/models_lion.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 173c2a794682a779 · report fixture: signature a_i:Tensor/2/float, L:int/0/int, start:int/0/int, end:int/0/int · returned Tensor · level recorded 2026-09-22
Casual_Mask_Selective_Partial img_classification/lion/models_lion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 74d6e1e65a29b46c · report fixture: signature vec:Tensor/3/float, chunk_index:int/0/int, chunk_len:int/0/int · returned Tensor · level recorded 2026-09-22
Causal_Mask_Decay img_classification/lion/models_lion.py ran · our draft was wrong fingerprinted licence not identified · pointer only · b7d6d1185456f649 · report fixture: signature a_i:Tensor/2/float, L:int/0/int · returned Tensor · level recorded 2026-09-22
Causal_Mask_Selective img_classification/lion/models_lion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only · ff5e874a04ef822f · report fixture: signature vec:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Lion_Attention img_classification/lion/models_lion.py ran · metamorphic tier: deterministic licence not identified · pointer only · 0fd20524afba58d9 · report fixture: returned Lion_Attention · level recorded 2026-09-22
compute_curve_order img_classification/lion/models_lion.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence not identified · pointer only · 96ac937123b116ca · report fixture: signature grid:list/1/list, orientation:str/0/str · returned list · level recorded 2026-09-22
coords_to_index img_classification/lion/models_lion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 4ef8a90a9ec9a0f6 · report fixture: signature grid:ndarray/2/int, coords:list/1/tuple · returned list · level recorded 2026-09-22
create_matrix_from_tensor img_classification/lion/models_lion.py ran · honoured contract fingerprinted licence not identified · pointer only · 233f32ffc1bfedb1 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22
create_matrix_from_tensor_backward img_classification/lion/models_lion.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 2c6f64b164f56782 · report fixture: signature tensor:Tensor/2/float, chunk_index:int/0/int, chunk_len:int/0/int · returned Tensor · level recorded 2026-09-22
create_matrix_from_tensor_forward img_classification/lion/models_lion.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 663e12d457f7ff82 · report fixture: signature tensor:Tensor/2/float, chunk_index:int/0/int, chunk_len:int/0/int · returned Tensor · level recorded 2026-09-22
elu_shifted img_classification/lion/models_lion.py ran · honoured contract fingerprinted licence not identified · pointer only · 90399293d39e23ac · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
index_to_coords_indexes img_classification/lion/models_lion.py ran · our draft was wrong licence not identified · pointer only · 882f6b4910fe627d · report fixture: signature coords:list/1/tuple, grid_width:int/0/int, grid_height:int/0/int · returned ndarray · level recorded 2026-09-22
s_curve img_classification/lion/models_lion.py ran · honoured contract licence not identified · pointer only · 5745d11adac3446b · report fixture: signature grid:list/1/list · returned list · level recorded 2026-09-22
silu_shifted img_classification/lion/models_lion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 19c5151cad5ba8a1 · report fixture: signature x:Tensor/2/float, silunorm:bool/0/bool · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LION (graph method: LION). 14 bricks; individually on a fixture: 14 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. Lion_Attention entry · level 1 · ran · 0fd20524afba58d9
  2. Casual_Mask_Decay_Partial helper · level 1 · ran · our draft was wrong · 173c2a794682a779
  3. Casual_Mask_Selective_Partial helper · level 1 · ran; the contract check could not run (RAISES) · 74d6e1e65a29b46c
  4. Causal_Mask_Decay helper · level 1 · ran · our draft was wrong · b7d6d1185456f649
  5. Causal_Mask_Selective helper · level 1 · ran; the contract check could not run (RAISES) · ff5e874a04ef822f
  6. compute_curve_order helper · level 1 · ran; the contract check could not run (RAISES) · 96ac937123b116ca
  7. coords_to_index helper · level 1 · ran; the contract check could not run (RAISES) · 4ef8a90a9ec9a0f6
  8. elu_shifted helper · level 1 · ran · honoured contract · 90399293d39e23ac
  9. index_to_coords_indexes helper · level 1 · ran · our draft was wrong · 882f6b4910fe627d
  10. silu_shifted helper · level 1 · ran; the contract check could not run (RAISES) · 19c5151cad5ba8a1
  11. create_matrix_from_tensor_backward helper · level 1 · ran · our draft was wrong · 2c6f64b164f56782
  12. create_matrix_from_tensor_forward helper · level 1 · ran · our draft was wrong · 663e12d457f7ff82
  13. create_matrix_from_tensor helper · level 1 · ran · honoured contract · 233f32ffc1bfedb1
  14. s_curve helper · level 1 · ran · honoured contract · 5745d11adac3446b

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2502.16249") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

State Space Models

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionLionSoftmax

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