Theme — multimodal

Items in corpus: 26

Papers

• Generalist biological AI — modeling the language of life — Rao et al., Nature Biotechnology, 2026
  Position paper unifying the five FM families.
• Beyond Alignment — Synergistic Information Score — bioRxiv (Microsoft), 2026
  Microsoft's metric for whether a multimodal FM extracts genuinely cross-modal information.
• Beyond Alignment — Synergistic Integration for Multimodal Cell FMs — preprint, 2026
  Argues multimodal cell-FMs need synergistic (not just aligned) integration.
• OmniCell — multimodal spatial FM — bioRxiv, 2025
  Multimodal spatial-transcriptomics FM.
• SpatialFusion — fusion of spatial data modalities — bioRxiv, 2026
  Multimodal spatial-transcriptomics integration FM.
• HEX — virtual spatial proteomics from histopathology for lung-cancer biomarkers — Xiang et al., Nature Medicine, 2026
  H&E → 40-protein spatial proteomics; +22% prognostic, +24-39% immunotherapy-response prediction across 2298 NSCLC patients.
• Multimodal clocks of human aging — Guang-Hui Liu et al., Cell, 2026
  mCAS cohort (2019 individuals) → core-capacity / multimodal / organ-specific aging clocks; MAE 3.87y on chronological age.
• KEEP — knowledge-enhanced pathology vision-language foundation model — MAGIC-AI4Med (SJTU + Shanghai AI Lab), Cancer Cell, 2025
  Knowledge-graph-conditioned pathology VLM from Shanghai Jiao Tong — Chinese answer to PathChat/Virchow.
• scTranslator — transcriptome→proteome generative model — Jianhua Yao et al., Nature Biomedical Engineering, 2025
  Tencent AI Lab — align-free scRNA→protein generation pretrained on 2M cells + 18k bulk samples.
• STAMP — single-cell transcriptomics + multimodal profiling through imaging — Qi Liu lab et al., Cell, 2025
  Turns Xenium/CosMx/MERSCOPE/PhenoCycler into scalable single-cell profilers — wet-lab counterpart to virtual spatial proteomics.
• DrugCLIP — contrastive protein-molecule virtual screening — NeurIPS 2023, 2023
  CLIP for protein-molecule retrieval — zero-shot virtual screen baseline that DrugReflector and successors build on.

Reviews

• AI revolutionizes cellular metabolic pathway reconstruction (AIVM review) — Trends in Biochemical Sciences, 2026
  Names the metabolism-flavoured AIVC subfield (AI Virtual Metabolism) as a coherent agenda.

Tools

• PathChat-DX — Mahmood Lab, 2025
  First generative-AI pathology tool with FDA Breakthrough Designation (Jan 2025).
• ESM-3 — Hayes et al. (EvolutionaryScale), Science, 2025
  98B-param multimodal protein FM; generated esmGFP de novo; cleanest compute disclosure.
• UNI — Nature Medicine, 2024
  Original Mahmood-lab pathology tile encoder.
• CONCH — Mahmood Lab
  Contrastive vision-language pathology FM.
• PathChat / PathChat-2 / PathChat-DX — Nature, 2024
  Mahmood vision-language pathology assistant; DX got FDA Breakthrough.
• BioMedCLIP
  Biomedical image–text contrastive model on large-scale figure–caption pairs.
• Med-Gemini — Google
  Google's medical multimodal model family for clinical reasoning and image Q&A.
• mSTAR — multimodal spatial-transcriptomics aggregation FM — Xu et al., Nature Communications, 2025
  Spatial pathology FM aggregating ST + WSI signals.
• PathChat-2 — Mahmood Lab, 2026
  Successor instruction-tuned pathology assistant (>1M pairs).

Organisations

• Mahmood Lab (Harvard / BWH / MGB) — Faisal Mahmood
  Full pathology vertical stack: UNI → TITAN → CONCH → PathChat; PathChat-DX FDA Breakthrough.
• Tempus AI
  Multimodal clinical AI; IPO June 2024.

People

• Faisal Mahmood — Harvard
  UNI, CONCH, PathChat, TITAN — most complete vertical pathology stack.
• Xi Peng — Xlearning Lab, Sichuan University
  Xlearning lab PI — multimodal-learning angle into virtual-cell territory.
• Jianhua Yao — Tencent AI Lab
  scTranslator PI, AIMBE fellow — Tencent's bio-FM lead.

---

Regenerated 2026-05-15 from a 277-item corpus by resourcelib-views.