{"paper":{"title":"ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawid Uchal, Eike Staub, Ewa Szczurek, Jakub Giezga{\\l}a, Kacper Pietrzyk, Karol Zagr\\'odka, Krzysztof Gogolewski, Marcin Mo\\.zejko, Mateusz Sulimowicz, Michal Orzy{\\l}owski, Piotr Kupidura, Robert Pieniuta, Szymon {\\L}ukasik, Tomasz Noco\\'n, Tomasz Si{\\l}kowski","submitted_at":"2026-02-04T14:11:33Z","abstract_excerpt":"We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that handles molecular marker measurements as image channels and enables large-scale spatial tissue profiling. Unlike natural images, multiplex imaging lacks a fixed channel space, as real-world marker sets vary across studies, violating a core assumption of standard vision backbones. To address this, ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate on arbitrary measured marker subsets without retraining.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embeddings learned from the pretraining marker set can generate effective kernels for entirely new marker combinations never seen during training or fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ImmuVis uses hyperconvolutions generated from marker embeddings to create a foundation model that processes variable marker subsets in IMC images, pretrained on 17M patches and providing uncertainty estimates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0fa647e8ba9407033be875e37594af57e5543dc680faba3e76565d204fb2303b"},"source":{"id":"2602.04585","kind":"arxiv","version":2},"verdict":{"id":"2ebcd494-a07f-4b68-8c39-be1f1ba40ce7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T07:32:09.971514Z","strongest_claim":"ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate on arbitrary measured marker subsets without retraining.","one_line_summary":"ImmuVis uses hyperconvolutions generated from marker embeddings to create a foundation model that processes variable marker subsets in IMC images, pretrained on 17M patches and providing uncertainty estimates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embeddings learned from the pretraining marker set can generate effective kernels for entirely new marker combinations never seen during training or fine-tuning.","pith_extraction_headline":"ImmuVis generates convolutional kernels on the fly from marker embeddings so one model works with any combination of molecular markers in tissue images."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}