{"total":67,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.07276","title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","created":"2023-10-11","cited_by_count":100,"area":null},{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96,"area":null},{"id":"2401.14656","title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","created":"2024-01-26","cited_by_count":80,"area":null},{"id":"2412.11427","title":"Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges","created":"2024-12-16","cited_by_count":41,"area":null},{"id":"2402.05200","title":"Are LLMs Ready for Real-World Materials Discovery?","created":"2024-02-07","cited_by_count":40,"area":null},{"id":"2307.14367","title":"Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers","created":"2023-07-25","cited_by_count":32,"area":null},{"id":"2310.03269","title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2310.03320","title":"BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs","created":"2023-10-05","cited_by_count":25,"area":null},{"id":"2405.12564","title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding","created":"2024-05-21","cited_by_count":25,"area":null},{"id":"2406.05540","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","created":"2024-06-08","cited_by_count":19,"area":null},{"id":"2402.09649","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","created":"2024-02-15","cited_by_count":18,"area":null},{"id":"2410.21317","title":"MatExpert: Decomposing Materials Discovery by Mimicking Human Experts","created":"2024-10-26","cited_by_count":18,"area":null},{"id":"2502.17504","title":"Protein Large Language Models: A Comprehensive Survey","created":"2025-02-21","cited_by_count":18,"area":null},{"id":"2403.01528","title":"Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey","created":"2024-03-03","cited_by_count":17,"area":null},{"id":"2303.06275","title":"A Systematic Study of Joint Representation Learning on Protein Sequences and Structures","created":"2023-03-11","cited_by_count":15,"area":null},{"id":"2405.06708","title":"LangCell: Language-Cell Pre-training for Cell Identity Understanding","created":"2024-05-09","cited_by_count":14,"area":null},{"id":"2307.11694","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2402.04286","title":"Progress and Opportunities of Foundation Models in Bioinformatics","created":"2024-02-06","cited_by_count":13,"area":null},{"id":"2406.09841","title":"Learning Multi-view Molecular Representations with Structured and Unstructured Knowledge","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2406.17295","title":"Less can be more for predicting properties with large language models","created":"2024-06-25","cited_by_count":11,"area":null},{"id":"2409.09825","title":"GP-GPT: Large Language Model for Gene-Phenotype Mapping","created":"2024-09-15","cited_by_count":11,"area":null},{"id":"2309.17255","title":"Knowledge Graphs for the Life Sciences: Recent Developments, Challenges and Opportunities","created":"2023-09-29","cited_by_count":10,"area":null},{"id":"2404.16866","title":"Annotation-guided Protein Design with Multi-Level Domain Alignment","created":"2024-04-18","cited_by_count":9,"area":null},{"id":"2401.17824","title":"A Survey of Pre-trained Language Models for Processing Scientific Text","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2503.09427","title":"Language-Enhanced Representation Learning for Single-Cell Transcriptomics","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2402.02287","title":"Future Directions in the Theory of Graph Machine Learning","created":"2024-02-03","cited_by_count":6,"area":null},{"id":"2407.19296","title":"Multi-Modal CLIP-Informed Protein Editing","created":"2024-07-27","cited_by_count":6,"area":null},{"id":"2501.10282","title":"Computational Protein Science in the Era of Large Language Models (LLMs)","created":"2025-01-17","cited_by_count":6,"area":null},{"id":"2403.13830","title":"Bridging Text and Molecule: A Survey on Multimodal Frameworks for Molecule","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2410.03553","title":"Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2506.14796","title":"PFMBench: Protein Foundation Model Benchmark","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2508.19667","title":"Survey of Specialized Large Language Model","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2402.13653","title":"PQA: Zero-shot Protein Question Answering for Free-form Scientific Enquiry with Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2403.15673","title":"AI for Biomedicine in the Era of Large Language Models","created":"2024-03-23","cited_by_count":3,"area":null},{"id":"2406.01651","title":"FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2406.05766","title":"Set-CLIP: Exploring Aligned Semantic From Low-Alignment Multimodal Data Through A Distribution View","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2501.06271","title":"Large Language Models for Bioinformatics","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2503.16659","title":"Advances in Protein Representation Learning: Methods, Applications, and Future Directions","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2306.11768","title":"Geometric Deep Learning for Structure-Based Drug Design: A Survey","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2310.00672","title":"GeRA: Label-Efficient Geometrically Regularized Alignment","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2408.00057","title":"GOProteinGNN: Leveraging Protein Knowledge Graphs for Protein Representation Learning","created":"2024-07-31","cited_by_count":2,"area":null},{"id":"2411.04863","title":"OneProt: Towards Multi-Modal Protein Foundation Models","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2411.11530","title":"SeqProFT: Sequence-only Protein Property Prediction with LoRA Finetuning","created":"2024-11-18","cited_by_count":2,"area":null},{"id":"2505.17911","title":"Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2507.20925","title":"Zero-Shot Learning with Subsequence Reordering Pretraining for Compound-Protein Interaction","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2405.17902","title":"Boosting Protein Language Models with Negative Sample Mining","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2405.19653","title":"SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2409.17726","title":"Recent advances in interpretable machine learning using structure-based protein representations","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2410.22949","title":"MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2504.03847","title":"Interpretable Multimodal Learning for Tumor Protein-Metal Binding: Progress, Challenges, and Perspectives","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2602.04916","title":"AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2405.06663","title":"Protein Representation Learning by Capturing Protein Sequence-Structure-Function Relationship","created":"2024-04-29","cited_by_count":0,"area":null},{"id":"2406.14142","title":"Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2410.15592","title":"CPE-Pro: A Structure-Sensitive Deep Learning Method for Protein Representation and Origin Evaluation","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2412.07678","title":"Can linguists better understand DNA?","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2503.04362","title":"A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2506.01376","title":"Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.08365","title":"AlphaFold Database Debiasing for Robust Inverse Folding","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2510.11188","title":"Protein as a Second Language for LLMs","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2511.03354","title":"Generative Artificial Intelligence in Bioinformatics: A Systematic Review of Models, Applications, and Methodological Advances","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2602.00862","title":"Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.17330","title":"SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.06722","title":"ProtAlign: Contrastive learning paradigm for Sequence and structure alignment","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.18505","title":"From Snapshots to Symphonies: The Evolution of Protein Prediction from Static Structures to Generative Dynamics and Multimodal Interactions","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.24489","title":"TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.02629","title":"Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding","created":"2026-05-30","cited_by_count":0,"area":null}],"next_cursor":null}