Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ha, Sumin, Kim, Jun Hyeong, Piao, Yinhua, Kim, Sun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.04780
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912263314604032
author Ha, Sumin
Kim, Jun Hyeong
Piao, Yinhua
Kim, Sun
author_facet Ha, Sumin
Kim, Jun Hyeong
Piao, Yinhua
Kim, Sun
contents Human expertise in chemistry and biomedicine relies on contextual molecular understanding, a capability that large language models (LLMs) can extend through fine-grained alignment between molecular structures and text. Recent multimodal learning advances focus on cross-modal alignment, but existing molecule-text models ignore complementary information in different molecular views and rely on single-view representations, limiting molecular understanding. Moreover, naïve multi-view alignment strategies face two challenges: (1) separate aligned spaces with inconsistent mappings between molecule and text embeddings, and that (2) existing loss objectives fail to preserve complementary information for fine-grained alignment. This can limit the LLM's ability to fully understand the molecular properties. To address these issues, we propose MV-CLAM, a novel framework that aligns multi-view molecular representations into a unified textual space using a multi-query transformer (MQ-Former). Our approach ensures cross-view consistency while a token-level contrastive loss preserves diverse molecular features across textual queries. MV-CLAM enhances molecular reasoning, improving retrieval and captioning accuracy. The source code of MV-CLAM is available in https://github.com/sumin124/mv-clam.git.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04780
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model
Ha, Sumin
Kim, Jun Hyeong
Piao, Yinhua
Kim, Sun
Computation and Language
Artificial Intelligence
Atomic Physics
Human expertise in chemistry and biomedicine relies on contextual molecular understanding, a capability that large language models (LLMs) can extend through fine-grained alignment between molecular structures and text. Recent multimodal learning advances focus on cross-modal alignment, but existing molecule-text models ignore complementary information in different molecular views and rely on single-view representations, limiting molecular understanding. Moreover, naïve multi-view alignment strategies face two challenges: (1) separate aligned spaces with inconsistent mappings between molecule and text embeddings, and that (2) existing loss objectives fail to preserve complementary information for fine-grained alignment. This can limit the LLM's ability to fully understand the molecular properties. To address these issues, we propose MV-CLAM, a novel framework that aligns multi-view molecular representations into a unified textual space using a multi-query transformer (MQ-Former). Our approach ensures cross-view consistency while a token-level contrastive loss preserves diverse molecular features across textual queries. MV-CLAM enhances molecular reasoning, improving retrieval and captioning accuracy. The source code of MV-CLAM is available in https://github.com/sumin124/mv-clam.git.
title MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model
topic Computation and Language
Artificial Intelligence
Atomic Physics
url https://arxiv.org/abs/2503.04780