SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.00101 · 2024

NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2409.00101.json · badge: /api/ran/2409.00101.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
935963004/neurolm canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
cosine_scheduler Ran
ran, honoured the contract we drafted
935963004/neurolm/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from boyazeng/understand_bias, is pointer only (licence: NONE) · get_code("b700fb0a3496b255")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from boyazeng/understand_bias, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_pred Ran
ran; our contract draft was wrong, not the code
935963004/neurolm/train_instruction.py
code served (permissive licence) · get_code("c26a6321cdb66be7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Test case 1: ZuCo dataset
pred_string_zuco = "some prefix text here" + "the prediction is here<|endoftext|>some suffix"
dataset_info_zuco = {
    'name': 'zuco'
}

# Test case 2: Non-ZuCo dataset with label dictionary
pred_string_other = "0 (A) result value"
dataset_info_other = {
    'name': 'other_dataset',
    'result_idx': 2,
    'label_dic': {
        '(A)': 0,
        '(B)': 1,
        '(C)': 2,
        'val': 3
    }
}

# Use the first test case
ARGS = {
    'pred_string': pred_string_zuco,
    'dataset_info': dataset_info_zuco
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
kmeans Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
935963004/neurolm/model/norm_ema_quantizer.py
code served (permissive licence) · get_code("4e63eaa872a45c44")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F
from einops import rearrange, repeat

torch.manual_seed(0)

# Create small sample tensor: (num_samples, dim)
# Using distinct dimensions: 2 samples, 4 features
samples = torch.randn(2, 4)

# Number of clusters
num_clusters = 2

# Number of iterations
num_iters = 10

# Use cosine similarity flag
use_cosine_sim = False

ARGS = {
    'samples': samples,
    'num_clusters': num_clusters,
    'num_iters': num_iters,
    'use_cosine_sim': use_cosine_sim
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
l2norm Ran
ran; our contract draft was wrong, not the code
935963004/neurolm/model/norm_ema_quantizer.py
pointer only (licence: MIT); the stored copy get_code serves, from jy0205/LaVIT, is pointer only (licence: NOASSERTION) · get_code("eca6cdf05972a95e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jy0205/LaVIT, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample_vectors Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
935963004/neurolm/model/norm_ema_quantizer.py
pointer only (licence: MIT); the stored copy get_code serves, from yangling0818/vqgraph, is pointer only (licence: NONE) · get_code("ada1d74afbd92171")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from yangling0818/vqgraph, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BuildEvents Not yet run
unverified (harvested, no recorded run)
935963004/neurolm/dataset_maker/prepare_HMC.py
code served (permissive licence) · get_code("dae1110e68d00ba3")
How it ran

no invocation recorded.

evaluate Not yet run
unverified (harvested, no recorded run)
935963004/neurolm/train_pretrain.py
code served (permissive licence) · get_code("46f04b20e87a817d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
cosine_scheduler 26 other papers
24 dated earlier, 1 later, 1 same year, order not determinable
1905.02244 (2019-05)
Searching for MobileNetV3
136810051 (2022 (year only))
AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
and 23 more not named here
l2norm 24 other papers
17 dated earlier, 7 later · 6 only as an assembly brick
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
2303.04341 (2023-03)
Neural Vector Fields: Implicit Representation by Explicit Learning
2303.04743 (2023-03)
Vector Quantized Time Series Generation with a Bidirectional Prior Model
and 21 more not named here
sample_vectors 15 other papers
9 dated earlier, 6 later · 5 only as an assembly brick
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2308.02117 (2023-08)
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
and 12 more not named here
kmeans 9 other papers
5 dated earlier, 4 later
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2309.16429 (2023-09)
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
and 6 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advancements for large-scale pre-training with neural signals such as electroencephalogram (EEG) have shown promising results, significantly boosting the development of brain-computer interfaces (BCIs) and healthcare. However, these pre-trained models often require full fine-tuning on each downstream task to achieve substantial improvements, limiting their versatility and usability, and leading to considerable resource wastage. To tackle these challenges, we propose NeuroLM, the first multi-task foundation model that leverages the capabilities of Large Language Models (LLMs) by regarding EEG signals as a foreign language, endowing the model with multi-task learning and inference capabilities. Our approach begins with learning a text-aligned neural tokenizer through vector-quantized temporal-frequency prediction, which encodes EEG signals into discrete neural tokens. These EEG tokens, generated by the frozen vector-quantized (VQ) encoder, are then fed into an LLM that learns causal EEG information via multi-channel autoregression. Consequently, NeuroLM can understand both EEG and language modalities. Finally, multi-task instruction tuning adapts NeuroLM to various downstream tasks. We are the first to demonstrate that, by specific incorporation with LLMs, NeuroLM unifies diverse EEG tasks within a single model through instruction tuning. The largest variant NeuroLM-XL has record-breaking 1.7B parameters for EEG signal processing, and is pre-trained on a large-scale corpus comprising approximately 25,000-hour EEG data. When evaluated on six diverse downstream datasets, NeuroLM showcases the huge potential of this multi-task learning paradigm.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.00101")
get_code_for_paper("2409.00101")
have("2409.00101")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.00101.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.00101.svg)](https://syntology.ai/paper/2409.00101)

Connect an agent — have() is free.