Papers › Quantized Spike-driven Transformer
Quantized Spike-driven Transformer
Xuerui Qiu, Jieyuan Zhang, Wenjie Wei, Honglin Cao, Junsheng Guo, Rui-Jie Zhu, Yimeng Shan, Yang Yang, Malu Zhang, Haizhou Li
Spiking neural networks are emerging as a promising energy-efficient alternative to traditional artificial neural networks due to their spike-driven paradigm. However, recent research in the SNN domain has mainly focused on enhancing accuracy by designing large-scale Transformer structures, which typically rely on substantial computational resources, limiting their deployment on resource-constrained devices. To overcome this challenge, we propose a quantized spike-driven Transformer baseline (QSD-Transformer), which achieves reduced resource demands by utilizing a low bit-width parameter. Regrettably, the QSD-Transformer often suffers from severe performance degradation. In this paper, we first conduct empirical analysis and find that the bimodal distribution of quantized spike-driven self-attention (Q-SDSA) leads to spike information distortion (SID) during quantization, causing significant performance degradation. To mitigate this issue, we take inspiration from mutual information entropy and propose a bi-level optimization strategy to rectify the information distribution in Q-SDSA. Specifically, at the lower level, we introduce an information-enhanced LIF to rectify the information distribution in Q-SDSA. At the upper level, we propose a fine-grained distillation scheme for the QSD-Transformer to align the distribution in Q-SDSA with that in the counterpart ANN. By integrating the bi-level optimization strategy, the QSD-Transformer can attain enhanced energy efficiency without sacrificing its high-performance advantage.For instance, when compared to the prior SNN benchmark on ImageNet, the QSD-Transformer achieves 80.3% top-1 accuracy, accompanied by significant reductions of 6.0× and 8.1× in power consumption and model size, respectively. Code is available at https://github.com/bollossom/QSD-Transformer.
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):
get_harvested_code_for_paper(arxiv_id="2501.13492")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2501.13492", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2501.13492")
Code
Syntology 25 code samples: 23 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 25: 13 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.
By repository: official repository: 23 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
25 samples harvested: 13 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 12 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.
Licence: 25 of the 25 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 bollossom/qsd-transformer. 2 samples are listed last, in a group without a repository. “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 8 samples 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.
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.
74d1ce63bd5f842a · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 f81565b0f74daf8b · report
fixture: returned BNAndPadLayer · level recorded 2026-09-22 fd8577cc6c4df32f · report
fixture: returned Conv1dLSQ · level recorded 2026-09-22 1df040edf15964ac · report
fixture: returned Conv2dLSQ · level recorded 2026-09-22 a68f1f39a2897fde · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 ff2a4847eb6e11d2 · report
fixture: returned Multispike · level recorded 2026-09-22 a9f9bdf13def2d6f · report
fixture: returned Multispike_att · level recorded 2026-09-22 ad6a0ecd94a89ea2 · report
fixture: returned ReLUX · level recorded 2026-09-22 86dd02836653f2e0 · report
fixture: returned _Conv2dQ · level recorded 2026-09-22 ded10a8feeb6a5ef · report
fixture: returned _LinearQ · level recorded 2026-09-22 82ae397418643fa2 · report
fixture: returned multispike · level recorded 2026-09-22 72e0098c41daeeaa · report
ec49ca703b82bffb · report
080509523416f672 · report
bcc18883fa271d08 · report
d439a7665ba3b641 · report
bc17ca45511f79e4 · report
dea3847a1c1fe943 · report
f1954be367964988 · report
32f1b759bc59a1b8 · report
3fbe93ab3bb68f7d · report
a4c658c06c77fb94 · report
1aaa70701617780d · report
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 0, kind float, dtype float32 repository not located ran · honoured contract fingerprinted licence of this copy not recorded ·
d75564df9359ef7b · report
fixture: signature x:Tensor/2/float, scale:Tensor/0/float · returned Tensor · level recorded 2026-09-22 census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 repository not located ran · honoured contract fingerprinted licence of this copy not recorded ·
40027e5e78ca8837 · report
fixture: signature x:Tensor/2/float · 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 QSD-Transformer (graph method: QSD-Transformer). 25 bricks; individually on a fixture: 13 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.
- Spiking_vit_MetaFormer entry · level 0 · unverified ·
32f1b759bc59a1b8 - LinearLSQ helper · level 1 · ran ·
a68f1f39a2897fde - MS_Block model · level 0 · unverified ·
ec49ca703b82bffb - MS_ConvBlock model · level 0 · unverified ·
080509523416f672 - MS_DownSampling model · level 0 · unverified ·
bcc18883fa271d08 - Multispike model · level 1 · ran ·
ff2a4847eb6e11d2 - ActLSQ helper · level 1 · ran ·
74d1ce63bd5f842a - Qmodes helper · level 0 · unverified ·
bc17ca45511f79e4 - _LinearQ helper · level 1 · ran ·
ded10a8feeb6a5ef - grad_scale helper · level 1 · ran · honoured contract ·
d75564df9359ef7b - round_pass helper · level 1 · ran · honoured contract ·
40027e5e78ca8837 - MS_Attention_RepConv_qkv_id model · level 0 · unverified ·
72e0098c41daeeaa - MS_MLP model · level 0 · unverified ·
d439a7665ba3b641 - Conv2dLSQ helper · level 1 · ran ·
1df040edf15964ac - SepConv model · level 0 · unverified ·
f1954be367964988 - multispike model · level 1 · ran ·
82ae397418643fa2 - _ActQ helper · level 0 · unverified ·
3fbe93ab3bb68f7d - get_default_kwargs_q helper · level 0 · unverified ·
1aaa70701617780d - Multispike_att model · level 1 · ran ·
a9f9bdf13def2d6f - RepConv model · level 0 · unverified ·
dea3847a1c1fe943 - Conv1dLSQ helper · level 1 · ran ·
fd8577cc6c4df32f - _Conv2dQ helper · level 1 · ran ·
86dd02836653f2e0 - BNAndPadLayer helper · level 1 · ran ·
f81565b0f74daf8b - _Conv1dQ helper · level 0 · unverified ·
a4c658c06c77fb94 - ReLUX helper · level 1 · ran ·
ad6a0ecd94a89ea2
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="2501.13492") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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