Papers › GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text

GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text

14 Aug 2023arXiv:2308.06911archive 2025-07-28

PengFei Liu, Yiming Ren, Jun Tao, Zhixiang Ren

Large language models have made significant strides in natural language processing, enabling innovative applications in molecular science by processing textual representations of molecules. However, most existing language models cannot capture the rich information with complex molecular structures or images. In this paper, we introduce GIT-Mol, a multi-modal large language model that integrates the Graph, Image, and Text information. To facilitate the integration of multi-modal molecular data, we propose GIT-Former, a novel architecture that is capable of aligning all modalities into a unified latent space. We achieve a 5%-10% accuracy increase in properties prediction and a 20.2% boost in molecule generation validity compared to the baselines. With the any-to-language molecular translation strategy, our model has the potential to perform more downstream tasks, such as compound name recognition and chemical reaction prediction.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.06911")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ai-hpc-research-team/git-mol officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong

Licence: 0 of the 1 sample are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ai-hpc-research-team/git-mol. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_latest_checkpoint ai-hpc-research-team/git-mol/train/pretrain.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 138b87fa967c256f · report

Tasks

Drug DiscoveryImage CaptioningLanguage ModelingLanguage ModellingLarge Language ModelMolecule CaptioningProperty PredictionText-based de novo Molecule Generationmolecular representation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Drug Discovery BACE GIT-Mol(G+S) AUC 0.8108 #6 of 6 Archive leaderboard report
Drug Discovery BBBP GIT-Mol(G+S) AUC 0.739 #3 of 4 Archive leaderboard report
Drug Discovery SIDER GIT-Mol(G+S) AUC 0.634 #3 of 4 Archive leaderboard report
Drug Discovery Tox21 GIT-Mol(G+S) AUC 0.759 #10 of 11 Archive leaderboard report
Drug Discovery ToxCast GIT-Mol(G+S) AUC 0.668 #4 of 5 Archive leaderboard report
Drug Discovery clintox GIT-Mol(G+S) AUC 0.883 #3 of 4 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol BLEU 0.924 #1 of 1 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol Exact 0.461 #1 of 1 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol Levenshtein 6.575 #1 of 1 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol MACCS FTS 0.962 #1 of 1 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol Morgan FTS 0.894 #1 of 1 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol RDK FTS 0.906 #1 of 1 Archive leaderboard report
Image Captioning ChEBI-20 GIT-Mol Validity 0.899 #1 of 1 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption BLEU 75.6 #16 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption Exact Match 5.1 #16 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption Levenshtein 26.315 #16 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption MACCS FTS 73.8 #16 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption Morgan FTS 51.9 #16 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption RDK FTS 58.2 #16 of 20 Archive leaderboard report
Text-based de novo Molecule Generation ChEBI-20 GIT-Mol-caption Validity 92.8 #16 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections