Papers › Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data

Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data

31 Oct 2023arXiv:2311.00136archive 2025-07-28

Antonis Antoniades, Yiyi Yu, Joseph Canzano, William Wang, Spencer LaVere Smith

State-of-the-art systems neuroscience experiments yield large-scale multimodal data, and these data sets require new tools for analysis. Inspired by the success of large pretrained models in vision and language domains, we reframe the analysis of large-scale, cellular-resolution neuronal spiking data into an autoregressive spatiotemporal generation problem. Neuroformer is a multimodal, multitask generative pretrained transformer (GPT) model that is specifically designed to handle the intricacies of data in systems neuroscience. It scales linearly with feature size, can process an arbitrary number of modalities, and is adaptable to downstream tasks, such as predicting behavior. We first trained Neuroformer on simulated datasets, and found that it both accurately predicted simulated neuronal circuit activity, and also intrinsically inferred the underlying neural circuit connectivity, including direction. When pretrained to decode neural responses, the model predicted the behavior of a mouse with only few-shot fine-tuning, suggesting that the model begins learning how to do so directly from the neural representations themselves, without any explicit supervision. We used an ablation study to show that joint training on neuronal responses and behavior boosted performance, highlighting the model's ability to associate behavioral and neural representations in an unsupervised manner. These findings show that Neuroformer can analyze neural datasets and their emergent properties, informing the development of models and hypotheses associated with the brain.

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 19 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 19 samples from 1 repository, 16 ran (16 with no instrument failure; 0 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

a-antoniades/neuroformer officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 16 ran (0 instrument-failed) · 3 unverified report
woanderer/Neuroformer officialmentioned on GitHubpytorchMITSyntology: 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.

Code Syntology ran Syntology

19 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 0 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 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.

1ran · honoured contract
15ran
3unverified

Licence: 0 of the 19 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 a-antoniades/neuroformer. “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.

a-antoniades/neuroformer official repository 19 samples, 16 ran (0 instrument-failed) · 3 unverified
calc_corr_psth neuroformer/analysis.py ran MIT (permissive) · d1186178a7836808 · report fixture: signature rates1:dict/0/?, rates2:dict/0/?, neurons:list/1/str · returned DataFrame · level recorded 2026-09-24
combo3_V1AL_callback neuroformer/datasets.py ran MIT (permissive) · 4c1a31f765ef032e · report fixture: signature frames:Tensor/4/float, frame_idx:int/0/int, n_frames:int/0/int, trial:int/0/int · returned Tensor · level recorded 2026-09-24
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
neuroformer/modules.py ran MIT (permissive) · d496ef53516a57ca · report fixture: signature features:dict/0/?, temp:float/0/float · returned Tensor · level recorded 2026-09-24
convolve_atts_3D neuroformer/attention_vis.py ran fingerprinted MIT (permissive) · ff4f6fdd29b64764 · report fixture: signature stim_atts:ndarray/4/float · returned ndarray · level recorded 2026-09-24
get_attr neuroformer/model_neuroformer.py ran MIT (permissive) · c3503f3549cd9acf · report fixture: signature obj:dict/0/?, name:str/0/str, default:NoneType/0/? · returned str · level recorded 2026-09-24
get_emb in 20 papers neuroformer/model_neuroformer.py ran · honoured contract fingerprinted MIT (permissive) · 33805df68cb6892e · report fixture: signature sin_inp:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_rates neuroformer/analysis.py ran MIT (permissive) · f2941cf251031ecc · report fixture: signature df:DataFrame/0/?, intervals:ndarray/1/float · returned tuple · level recorded 2026-09-24
get_rates neuroformer/analysis.py ran MIT (permissive) · 2398af86975c9957 · report fixture: signature df:DataFrame/0/?, ids:list/1/int, intervals:list/1/str, interval:str/0/str · returned dict · level recorded 2026-09-24
model_ensemble neuroformer/simulation.py ran MIT (permissive) · 30d823e13e046f0b · report fixture: signature models:list/1/callable, x:Tensor/2/float · returned dict · level recorded 2026-09-24
rollout_attentions neuroformer/attention_vis.py ran fingerprinted MIT (permissive) · 861a7367a2ed59cd · report fixture: signature att:Tensor/4/float · returned Tensor · level recorded 2026-09-24
separate_eos_tokens neuroformer/modules.py ran MIT (permissive) · 2e9f1a5673215030 · report fixture: signature eos_id_tok:int/0/int, eos_dt_tok:int/0/int, targets:dict/0/?, id_logits:Tensor/3/float, dt_logits:Tensor/3/float · returned tuple · level recorded 2026-09-24
split_data_by_interval neuroformer/datasets.py ran MIT (permissive) · 015233a9d8a82fc1 · report fixture: signature intervals:ndarray/2/float, r_split:float/0/float, r_split_ft:float/0/float · returned tuple · level recorded 2026-09-24
trial_df neuroformer/data_utils.py ran MIT (permissive) · a9af76e30c2a8e46 · report fixture: signature data:list/1/ndarray · returned DataFrame · level recorded 2026-09-24
trial_df_combo3 neuroformer/data_utils.py ran MIT (permissive) · 2afb4903a5098278 · report fixture: signature data:list/1/ndarray, n_stim:int/0/int · returned DataFrame · level recorded 2026-09-24
trial_df_real neuroformer/data_utils.py ran MIT (permissive) · 8ad3185a7b0c4d25 · report fixture: signature data:list/1/ndarray · returned DataFrame · level recorded 2026-09-24
visnav_callback neuroformer/datasets.py ran fingerprinted MIT (permissive) · dc18b01aaf085b2c · report fixture: signature frames:Tensor/4/float, frame_idx:int/0/int, n_frames:int/0/int · returned Tensor · level recorded 2026-09-24
nearest neuroformer/gather_atts.py unverified MIT (permissive) · 62b7dc6a0fcb3055 · report
reshape_features neuroformer/attention_vis.py unverified MIT (permissive) · 99fdd80b9ca7f208 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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