{"type":"ScholarlyArticle","title":"Unified Molecule-Text Language Model with Discrete Token Representation","authors":[{"name":"Shuhan Guo","slug":"shuhan-guo","given":"Shuhan","family":"Guo","affiliation":""},{"name":"Yatao Bian","slug":"yatao-bian","given":"Yatao","family":"Bian","affiliation":""},{"name":"Ruibing Wang","slug":"ruibing-wang","given":"Ruibing","family":"Wang","affiliation":""},{"name":"Nan Yin","slug":"nan-yin","given":"Nan","family":"Yin","affiliation":""},{"name":"Zhen Wang","slug":"zhen-wang","given":"Zhen","family":"Wang","affiliation":""},{"name":"Quanming Yao","slug":"quanming-yao","given":"Quanming","family":"Yao","affiliation":""}],"abstract":"The remarkable success of Large Language Models (LLMs) across diverse tasks has driven the research community to extend their capabilities to molecular applications. However, most molecular LLMs employ adapter-based architectures that fail to equally integrate molecule and text modalities and lack explicit supervision signals for the molecular modality. To address these issues, we introduce UniMoT, a Unified Molecule-Text LLM adopting a tokenizer-based architecture that expands the vocabulary of LLMs with molecule tokens. Specifically, we introduce a Vector Quantization-driven tokenizer that incorporates a Q-Former to bridge the modality gap between molecule and text. This tokenizer transforms molecular structures into sequences of  tokens exhibiting causal dependency, thereby encapsulating both  high-level molecular features and textual information. Equipped with this tokenizer, UniMoT  unifies molecule and text modalities under a shared token representation and an autoregressive training paradigm. This enables the model to process molecular structures as a distinct linguistic system and generate them in textual form. Through a four-stage training scheme, UniMoT functions as a multi-modal generalist capable of performing both molecule-to-text and text-to-molecule tasks. Extensive experiments demonstrate that UniMoT achieves state-of-the-art performance across a wide range of molecule comprehension and generation tasks.","doi":"10.24963/ijcai.2025/1023","url":"https://ijcai.org/proceedings/2025/1023","pdf":"https://ijcai.org/proceedings/2025/1023.pdf","markdown":"https://ijcai.org/proceedings/2025/1023.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1023","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI4Tech: AI Enabling Technologies","track":"AI4Tech: AI Enabling Technologies","number":1023,"pages":{"first":9205,"last":9213},"keywords":["Advanced AI4Tech: AI4Tech foundations","Advanced AI4Tech: Multimodal AI4Tech","Emerging AI4Tech: Emerging AI4Tech areas","Advanced AI4Tech: Data-driven AI4Tech"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}