{"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/state-space-models-as-foundation-models-a","title":"State Space Models as Foundation Models: A Control Theoretic Overview","arxiv_id":"2403.16899","date":"2024-03-25","proceeding":null,"authors":["Carmen Amo Alonso","Jerome Sieber","Melanie N. Zeilinger"],"abstract":"In recent years, there has been a growing interest in integrating linear state-space models (SSM) in deep neural network architectures of foundation models. This is exemplified by the recent success of Mamba, showing better performance than the state-of-the-art Transformer architectures in language tasks. Foundation models, like e.g. GPT-4, aim to encode sequential data into a latent space in order to learn a compressed representation of the data. The same goal has been pursued by control theorists using SSMs to efficiently model dynamical systems. Therefore, SSMs can be naturally connected to deep sequence modeling, offering the opportunity to create synergies between the corresponding research areas. This paper is intended as a gentle introduction to SSM-based architectures for control theorists and summarizes the latest research developments. It provides a systematic review of the most successful SSM proposals and highlights their main features from a control theoretic perspective. Additionally, we present a comparative analysis of these models, evaluating their performance on a standardized benchmark designed for assessing a model's efficiency at learning long sequences.","url_abs":"https://arxiv.org/abs/2403.16899v1","url_pdf":"https://arxiv.org/pdf/2403.16899v1.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":"state-space-models-as-foundation-models-a","repo_url":"https://github.com/jsie7/ssm-benchmark","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.16899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16899"}},"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/jsie7/ssm-benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":"3a90c1c4dfa2d30d","entry":"init_forget_gate","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"models/hawk.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/models/hawk.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":"3a90c1c4dfa2d30d"}},{"code_sha256_prefix":"ba7b868fec181b57","entry":"selective_scan_ref","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/ops/selective_scan_interface.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/ops/selective_scan_interface.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":"ba7b868fec181b57"}},{"code_sha256_prefix":"eda7b73324d5e67e","entry":"decode","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/utils/generation.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/utils/generation.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":"eda7b73324d5e67e"}},{"code_sha256_prefix":"2ce8fcf5bedd19ec","entry":"layer_norm_ref","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/ops/triton/layernorm.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/ops/triton/layernorm.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":"2ce8fcf5bedd19ec"}},{"code_sha256_prefix":"7a8ab4bf37f8fa41","entry":"load_config_hf","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/utils/hf.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/utils/hf.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":"7a8ab4bf37f8fa41"}},{"code_sha256_prefix":"70607b36f7d19351","entry":"load_state_dict_hf","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/utils/hf.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/utils/hf.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":"70607b36f7d19351"}},{"code_sha256_prefix":"da95e9a7906f3d52","entry":"modify_logit_for_repetition_penalty","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/utils/generation.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/utils/generation.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":"da95e9a7906f3d52"}},{"code_sha256_prefix":"ab802ae3195c6316","entry":"rms_norm_ref","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/ops/triton/layernorm.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/ops/triton/layernorm.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":"ab802ae3195c6316"}},{"code_sha256_prefix":"8eafd3cf90152c82","entry":"sample","repo":"jsie7/ssm-benchmark","repo_kind":"official","path":"mamba-1.1.4/mamba_ssm/utils/generation.py","file_url":"https://github.com/jsie7/ssm-benchmark/blob/HEAD/mamba-1.1.4/mamba_ssm/utils/generation.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":"8eafd3cf90152c82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}