Metraipolis › archive › dc_47c09bb138a5
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models — arXiv:2608.23646
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23646
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:31.982Z
- SHA-256 of the archived text
5116543c336d376df43ab23cbca899b6ca2263963df08d56a3a0916b5b915c0d- Stable URL of this page
https://metraipolis.com/documento/dc_47c09bb138a5
How to cite
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models — arXiv:2608.23646 — arXiv (en), https://arxiv.org/abs/2608.23646 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47c09bb138a5 (Metraipolis archive dc_47c09bb138a5, sha256 5116543c336d376df43ab23cbca899b6ca2263963df08d56a3a0916b5b915c0d)
BibTeX
@misc{dc47c09bb138a5,
title = {MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models — arXiv:2608.23646},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23646},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47c09bb138a5; sha256 5116543c336d376df43ab23cbca899b6ca2263963df08d56a3a0916b5b915c0d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23646. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Molecular embedding models can serve as foundational infrastructure for computational chemistry and drug discovery, where reusable vector representations support property prediction, virtual screening, and retrieval. Most molecular encoders are specialist models built around a single molecular view, producing unconditional vectors with no language interface for varying the representation. We ask whether multimodal large language models (MLLMs), which natively process images, text, and symbolic inputs, can instead serve as \emph{general molecular embedding models} that produce embeddings conditioned on both a molecular profile and a natural-language semantic context. We introduce \textbf{MolEmb}, a lightweight framework that adapts MLLMs by aligning molecular profiles with textual descriptions in a shared embedding space using a bidirectional contrastive objective. The resulting embedding model is competitive on molecular property prediction and supports cross-modal molecule--text retrieval in the same space. We further introduce \textbf{MolCAR}, a diagnostic benchmark for context-aware retrieval, and find that context-aware molecular embedding is primarily a data property of the supervision. These results suggest that MLLMs are not merely chemistry assistants or generators, but a viable and extensible route to general molecular embedding models.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.23646 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:28:52.303Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).