{"paper":{"title":"Memristor Technologies for Dynamic Vision Sensors: A Critical Assessment and Research Roadmap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An end-to-end integrated DVS-memristor system is the field's open challenge, with concrete accuracy and power targets.","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Edris Zaman Farsa, Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad","submitted_at":"2026-05-13T15:51:05Z","abstract_excerpt":"Edge-AI deployment is bottlenecked by data-movement energy; pairing event-driven vision sensors with in-memory analog compute could lift that ceiling by orders of magnitude. Both technologies are individually mature; the framework distinguishing fabricated demonstrations from projected systems is missing. Of six application domains surveyed (robotics, autonomous vehicles, AR/VR, surveillance, medical imaging, IoT), half rest entirely on projection, and existing hardware sits at Technology Readiness Levels 2-5. This evidence-graded review applies a three-paradigm architectural taxonomy and benc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"An end-to-end integrated DVS-memristor system is the field's open challenge, with testable accuracy and power targets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the projected orders-of-magnitude energy gains from analog in-memory compute will be realized in fabricated systems beyond the current TRL 2-5 demonstrations surveyed.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A structured review concludes that end-to-end DVS-memristor integration for analog in-memory event-driven computing remains an open challenge at TRL 2-5, with half of surveyed applications resting on projections rather than demonstrations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An end-to-end integrated DVS-memristor system is the field's open challenge, with concrete accuracy and power targets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a6681c7bc810ba70b42f75dc75d7fd37a21f584b86d9f16ff88af597c283c5c5"},"source":{"id":"2605.13699","kind":"arxiv","version":1},"verdict":{"id":"8293636b-5652-43f1-9a22-78d739eb42fc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T17:42:37.543630Z","strongest_claim":"An end-to-end integrated DVS-memristor system is the field's open challenge, with testable accuracy and power targets.","one_line_summary":"A structured review concludes that end-to-end DVS-memristor integration for analog in-memory event-driven computing remains an open challenge at TRL 2-5, with half of surveyed applications resting on projections rather than demonstrations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the projected orders-of-magnitude energy gains from analog in-memory compute will be realized in fabricated systems beyond the current TRL 2-5 demonstrations surveyed.","pith_extraction_headline":"An end-to-end integrated DVS-memristor system is the field's open challenge, with concrete accuracy and power targets."},"references":{"count":151,"sample":[{"doi":"","year":2008,"title":"A 128×128 120 dB 15µs latency asynchronous temporal contrast vision sensor,","work_id":"ae37c3df-3194-481a-9402-6cac6231743a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"In-memory computing with resistive switching devices,","work_id":"6c6bfe0d-1f94-4424-917b-a9b22f72edbc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Memory devices and applications for in-memory computing,","work_id":"0b334d44-ac50-4043-8a31-260e7f47adb0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"The missing memristor found,","work_id":"ee038e5c-7926-4f7e-a36c-e9ffdbbbd9de","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Training and operation of an integrated neuromorphic network based on metal- oxide memristors,","work_id":"8870466e-abca-4835-9362-e2d2e4b53790","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":151,"snapshot_sha256":"a9f91ddade15ff6fcb4caac0d9a82a09317366738e9c05adf959b70d951a96c9","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f8fa8db8300d2086a29ee66aa4be18c56c4cbc0fb627795a26e3189639a61169"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}