{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neurolm-a-universal-multi-task-foundation","title":"NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals","arxiv_id":"2409.00101","date":"2024-08-27","proceeding":null,"authors":["Wei-Bang Jiang","Yansen Wang","Bao-liang Lu","Dongsheng Li"],"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.","url_abs":"https://arxiv.org/abs/2409.00101v3","url_pdf":"https://arxiv.org/pdf/2409.00101v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neurolm-a-universal-multi-task-foundation","repo_url":"https://github.com/935963004/neurolm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.00101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00101"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/935963004/neurolm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c26a6321cdb66be7","entry":"get_pred","repo":"935963004/neurolm","repo_kind":"official","path":"train_instruction.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/train_instruction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c26a6321cdb66be7"}},{"code_sha256_prefix":"eca6cdf05972a95e","entry":"l2norm","repo":"935963004/neurolm","repo_kind":"official","path":"model/norm_ema_quantizer.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/model/norm_ema_quantizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eca6cdf05972a95e"}},{"code_sha256_prefix":"ada1d74afbd92171","entry":"sample_vectors","repo":"935963004/neurolm","repo_kind":"official","path":"model/norm_ema_quantizer.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/model/norm_ema_quantizer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ada1d74afbd92171"}},{"code_sha256_prefix":"dae1110e68d00ba3","entry":"BuildEvents","repo":"935963004/neurolm","repo_kind":"official","path":"dataset_maker/prepare_HMC.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/dataset_maker/prepare_HMC.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dae1110e68d00ba3"}},{"code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"935963004/neurolm","repo_kind":"official","path":"utils.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b700fb0a3496b255"}},{"code_sha256_prefix":"46f04b20e87a817d","entry":"evaluate","repo":"935963004/neurolm","repo_kind":"official","path":"train_pretrain.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/train_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46f04b20e87a817d"}},{"code_sha256_prefix":"4e63eaa872a45c44","entry":"kmeans","repo":"935963004/neurolm","repo_kind":"official","path":"model/norm_ema_quantizer.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/model/norm_ema_quantizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e63eaa872a45c44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}