Papers › Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models

Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models

29 Apr 2024arXiv:2404.18508archive 2025-07-28

Mark Schöne, Neeraj Mohan Sushma, Jingyue Zhuge, Christian Mayr, Anand Subramoney, David Kappel

Event-based sensors are well suited for real-time processing due to their fast response times and encoding of the sensory data as successive temporal differences. These and other valuable properties, such as a high dynamic range, are suppressed when the data is converted to a frame-based format. However, most current methods either collapse events into frames or cannot scale up when processing the event data directly event-by-event. In this work, we address the key challenges of scaling up event-by-event modeling of the long event streams emitted by such sensors, which is a particularly relevant problem for neuromorphic computing. While prior methods can process up to a few thousand time steps, our model, based on modern recurrent deep state-space models, scales to event streams of millions of events for both training and inference. We leverage their stable parameterization for learning long-range dependencies, parallelizability along the sequence dimension, and their ability to integrate asynchronous events effectively to scale them up to long event streams. We further augment these with novel event-centric techniques enabling our model to match or beat the state-of-the-art performance on several event stream benchmarks. In the Spiking Speech Commands task, we improve state-of-the-art by a large margin of 7.7% to 88.4%. On the DVS128-Gestures dataset, we achieve competitive results without using frames or convolutional neural networks. Our work demonstrates, for the first time, that it is possible to use fully event-based processing with purely recurrent networks to achieve state-of-the-art task performance in several event-based benchmarks.

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 18 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 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: 18 samples from 1 repository, 15 ran (10 with no instrument failure; 5 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Efficient-Scalable-Machine-Learning/event-ssm officialmentioned in papermentioned on GitHubjaxMITSyntology: 18 samples, 15 ran (5 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

18 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 2 violated, 7 with no contract checked; 5 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.

1ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
7ran
3unverified

Licence: 0 of the 18 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 Efficient-Scalable-Machine-Learning/event-ssm. “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.

Efficient-Scalable-Machine-Learning/event-ssm official repository 18 samples, 15 ran (5 instrument-failed) · 3 unverified
cut_mix_augmentation event_ssm/transform.py ran MIT (permissive) · 801be17d5a9e3d5d · report fixture: signature events:list/1/ndarray, targets:ndarray/1/float · returned tuple · level recorded 2026-09-24
cut_mix_augmentation_time event_ssm/transform.py ran MIT (permissive) · 878ef192b1e8192e · report fixture: signature events:list/1/ndarray, targets:ndarray/2/float · returned tuple · level recorded 2026-09-24
discretize_dirac event_ssm/ssm.py ran MIT (permissive) · 9e888aab5e750287 · report fixture: signature Lambda:ArrayImpl/1/complex, step_delta:ArrayImpl/1/float, time_delta:ArrayImpl/0/float · returned tuple · level recorded 2026-09-24
discretize_zoh in 8 papers event_ssm/ssm.py ran MIT (permissive) · bb3aeee6201c06dd · report fixture: signature Lambda:ArrayImpl/1/complex, step_delta:ArrayImpl/1/float, time_delta:ArrayImpl/0/float · returned tuple · level recorded 2026-09-24
evaluation_step event_ssm/train_utils.py ran MIT (permissive) · 7905962f8670b1da · report fixture: signature train_state:TrainState/0/?, batch:tuple/1/ArrayImpl, distributed:bool/0/bool · returned tuple · level recorded 2026-09-24
evaluation_step run_evaluation.py ran MIT (permissive) · 1b34fdae353a499d · report fixture: signature apply_fn:callable/0/?, params:dict/0/?, model_state:dict/0/?, batch:tuple/1/ArrayImpl · returned tuple · level recorded 2026-09-24
event_stream_dataloader event_ssm/dataloading.py ran MIT (permissive) · e0293591386f80aa · report fixture: signature train_data:SimpleDataset/0/?, val_data:SimpleDataset/0/?, test_data:SimpleDataset/0/?, batch_size:int/0/int, eval_batch_size:int/0/int, train_collate_fn:callable/0/?, eval_collate_fn:callable/0/?, rng:Generator/0/?, num_workers:int/0/int, shuffle_training:bool/0/bool · returned tuple · level recorded 2026-09-24
make_DPLR_HiPPO in 5 papers event_ssm/ssm_init.py ran · our draft was wrong fingerprinted MIT (permissive) · 188626e586495ec6 · report fixture: signature N:int/0/int · returned tuple · level recorded 2026-09-24
make_HiPPO in 5 papers event_ssm/ssm_init.py ran · honoured contract MIT (permissive) · 27e9e05de680bfb5 · report fixture: signature N:int/0/int · returned ArrayImpl · level recorded 2026-09-24
make_NPLR_HiPPO in 5 papers event_ssm/ssm_init.py ran · our draft was wrong fingerprinted MIT (permissive) · 17177c94dcd9bfbf · report fixture: signature N:int/0/int · returned tuple · level recorded 2026-09-24
map_nested_fn event_ssm/train_utils.py ran · our draft was wrong MIT (permissive) · 50b98382b2de060e · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-24
masked_meanpool in 5 papers event_ssm/seq_model.py ran · violated contract MIT (permissive) · f2a2429ab2b145a5 · report fixture: signature x:ArrayImpl/2/float, lengths:int/0/int · returned ArrayImpl · level recorded 2026-09-24
reshape_array_per_device event_ssm/trainer.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d0d2c7cc8a0e8597 · report fixture: signature x:Tensor/3/float, num_devices:int/0/int · returned Tensor · level recorded 2026-09-24
reshape_batch_per_device event_ssm/trainer.py ran · our draft was wrong MIT (permissive) · 0512fd084f8551e4 · report fixture: signature x:dict/0/?, num_devices:int/0/int · returned dict · level recorded 2026-09-24
timepool event_ssm/seq_model.py ran · violated contract MIT (permissive) · b03910f5f285bbc7 · report fixture: signature x:ArrayImpl/2/float, integration_timesteps:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-24
discretize_async event_ssm/ssm.py unverified MIT (permissive) · b84da31f714379cb · report
masked_timepool event_ssm/seq_model.py unverified MIT (permissive) · de3055769b640635 · report
training_step in 10 papers event_ssm/train_utils.py unverified MIT (permissive) · 5f8147f4c2b3b6c4 · report

Tasks

Audio ClassificationGesture RecognitionHand-Gesture RecognitionState Space Models

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Classification SHD Event-SSM Percentage correct 95.9 #1 of 11 Archive leaderboard report
Audio Classification SSC Event-SSM Accuracy 88.4 #1 of 5 Archive leaderboard report
Gesture Recognition DVS128 Gesture Event-SSM Accuracy (%) 97.7 #6 of 14 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