{"url":"/task/molecular-representation","name":"molecular representation","slug":"molecular-representation","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":168,"papers_with_code":87,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":87,"tagged_in_all":168,"items":[{"url":"/paper/3d-equivariant-molecular-graph-pretraining","title":"Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs","date":"2022-07-18","arxiv_id":"2207.08824","repositories_listed":5,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","date":"2019-04-02","arxiv_id":"1904.01561","repositories_listed":4,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/chemberta-large-scale-self-supervised","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","date":"2020-10-19","arxiv_id":"2010.09885","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/grover-self-supervised-message-passing","title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data","date":"2020-06-18","arxiv_id":"2007.02835","repositories_listed":3,"syntology":null},{"url":"/paper/the-role-of-model-architecture-and-scale-in","title":"The Role of Model Architecture and Scale in Predicting Molecular Properties: Insights from Fine-Tuning RoBERTa, BART, and LLaMA","date":"2024-05-02","arxiv_id":"2405.00949","repositories_listed":2,"syntology":null},{"url":"/paper/comparative-analysis-of-llama-and-chatgpt","title":"Can Large Language Models Understand Molecules?","date":"2024-01-05","arxiv_id":"2402.00024","repositories_listed":2,"syntology":null},{"url":"/paper/uncovering-neural-scaling-laws-in-molecular-1","title":"Uncovering Neural Scaling Laws in Molecular Representation Learning","date":"2023-09-15","arxiv_id":"2309.15123","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/muben-benchmarking-the-uncertainty-of-pre","title":"MUBen: Benchmarking the Uncertainty of Molecular Representation Models","date":"2023-06-14","arxiv_id":"2306.10060","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/uni-qsar-an-auto-ml-tool-for-molecular","title":"Uni-QSAR: an Auto-ML Tool for Molecular Property Prediction","date":"2023-04-24","arxiv_id":"2304.12239","repositories_listed":2,"syntology":null},{"url":"/paper/a-systematic-survey-of-molecular-pre-trained","title":"A Systematic Survey of Chemical Pre-trained Models","date":"2022-10-29","arxiv_id":"2210.16484","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/molecular-geometry-pretraining-with-se-3","title":"Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching","date":"2022-06-27","arxiv_id":"2206.13602","repositories_listed":2,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/ssi-ddi-substructure-substructure","title":"SSI–DDI: Substructure–Substructure Interactions for Drug–Drug Interaction Prediction","date":"2021-11-07","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multiresolution-graph-variational-autoencoder","title":"Multiresolution Equivariant Graph Variational Autoencoder","date":"2021-06-02","arxiv_id":"2106.00967","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":6}},{"url":"/paper/molecular-representation-learning-with","title":"Molecular representation learning with language models and domain-relevant auxiliary tasks","date":"2020-11-26","arxiv_id":"2011.13230","repositories_listed":2,"syntology":null},{"url":"/paper/selfies-a-robust-representation-of","title":"Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation","date":"2019-05-31","arxiv_id":"1905.13741","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-continuous-and-data-driven-molecular","title":"Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical Representations","date":"2018-11-19","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/molecular-machine-learning-using-euler","title":"Molecular Machine Learning Using Euler Characteristic Transforms","date":"2025-07-04","arxiv_id":"2507.03474","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/2dnmrgym-an-annotated-experimental-dataset","title":"2DNMRGym: An Annotated Experimental Dataset for Atom-Level Molecular Representation Learning in 2D NMR via Surrogate Supervision","date":"2025-05-16","arxiv_id":"2505.18181","repositories_listed":1,"syntology":null},{"url":"/paper/molspectra-pre-training-3d-molecular","title":"MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra","date":"2025-02-22","arxiv_id":"2502.16284","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":12}},{"url":"/paper/unimatch-universal-matching-from-atom-to-task","title":"UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery","date":"2025-02-18","arxiv_id":"2502.12453","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/gdiffretro-retrosynthesis-prediction-with","title":"GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation","date":"2025-01-14","arxiv_id":"2501.08001","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/mol-mamba-enhancing-molecular-representation","title":"MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights","date":"2024-12-21","arxiv_id":"2412.16483","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/bapulm-binding-affinity-prediction-using","title":"BAPULM: Binding Affinity Prediction using Language Models","date":"2024-11-06","arxiv_id":"2411.04150","repositories_listed":1,"syntology":null},{"url":"/paper/chemical-language-model-linker-blending-text","title":"Chemical Language Model Linker: blending text and molecules with modular adapters","date":"2024-10-26","arxiv_id":"2410.20182","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-biomedical-foundation-models-for","title":"Multi-view biomedical foundation models for molecule-target and property prediction","date":"2024-10-25","arxiv_id":"2410.19704","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/molmix-a-simple-yet-effective-baseline-for","title":"MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning","date":"2024-10-10","arxiv_id":"2410.07981","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/molecular-graph-representation-learning-via","title":"Molecular Graph Representation Learning via Structural Similarity Information","date":"2024-09-13","arxiv_id":"2409.08580","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-of-molecular-data-for-task","title":"Active Learning of Molecular Data for Task-Specific Objectives","date":"2024-08-20","arxiv_id":"2408.11191","repositories_listed":1,"syntology":null},{"url":"/paper/geomformer-a-general-architecture-for","title":"GeoMFormer: A General Architecture for Geometric Molecular Representation Learning","date":"2024-06-24","arxiv_id":"2406.16853","repositories_listed":1,"syntology":null},{"url":"/paper/learning-molecular-representation-in-a-cell","title":"Learning Molecular Representation in a Cell","date":"2024-06-17","arxiv_id":"2406.12056","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}