{"total":77,"rows":[{"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":"2401.14656","title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","created":"2024-01-26","cited_by_count":80,"area":null},{"id":"2301.12040","title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts","created":"2023-01-28","cited_by_count":78,"area":null},{"id":"2402.17810","title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","created":"2024-02-27","cited_by_count":54,"area":null},{"id":"2301.06568","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2311.12570","title":"BEND: Benchmarking DNA Language Models on biologically meaningful tasks","created":"2023-11-21","cited_by_count":29,"area":null},{"id":"2402.08703","title":"A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation","created":"2024-02-13","cited_by_count":29,"area":null},{"id":"2403.00485","title":"A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2403.07920","title":"ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training","created":"2024-02-28","cited_by_count":21,"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":"2406.09098","title":"SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models","created":"2024-06-13","cited_by_count":19,"area":null},{"id":"2502.17504","title":"Protein Large Language Models: A Comprehensive Survey","created":"2025-02-21","cited_by_count":18,"area":null},{"id":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17,"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":"2406.13864","title":"Evaluating representation learning on the protein structure universe","created":"2024-06-19","cited_by_count":16,"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":"2503.00089","title":"Protein Structure Tokenization: Benchmarking and New Recipe","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","cited_by_count":15,"area":null},{"id":"2309.05934","title":"MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling","created":"2023-09-12","cited_by_count":14,"area":null},{"id":"2502.16533","title":"A Survey of Graph Transformers: Architectures, Theories and Applications","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2301.12068","title":"Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction","created":"2023-01-28","cited_by_count":13,"area":"diffusion"},{"id":"2407.00002","title":"Kermut: Composite kernel regression for protein variant effects","created":"2024-04-09","cited_by_count":12,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","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":"2407.00236","title":"Closed-Form Test Functions for Biophysical Sequence Optimization Algorithms","created":"2024-06-28","cited_by_count":8,"area":null},{"id":"2503.04013","title":"Benchmarking Large Language Models on Multiple Tasks in Bioinformatics NLP with Prompting","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2207.00982","title":"Linguistically inspired roadmap for building biologically reliable protein language models","created":"2022-07-03","cited_by_count":7,"area":null},{"id":"2302.12563","title":"Retrieved Sequence Augmentation for Protein Representation Learning","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2406.10391","title":"BEACON: Benchmark for Comprehensive RNA Tasks and Language Models","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2402.05856","title":"Structure-Informed Protein Language Model","created":"2024-02-07","cited_by_count":6,"area":null},{"id":"2404.14850","title":"Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language Models","created":"2024-04-23","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":"2505.11812","title":"VenusX: Unlocking Fine-Grained Functional Understanding of Proteins","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2409.14617","title":"Protein-Mamba: Biological Mamba Models for Protein Function Prediction","created":"2024-09-22","cited_by_count":4,"area":"ssm"},{"id":"2410.22367","title":"MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2505.20354","title":"Rethinking Text-based Protein Understanding: Retrieval or LLM?","created":"2025-05-26","cited_by_count":4,"area":"lr"},{"id":"2506.14796","title":"PFMBench: Protein Foundation Model Benchmark","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2410.08355","title":"Metalic: Meta-Learning In-Context with Protein Language Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2209.12635","title":"ImmunoLingo: Linguistics-based formalization of the antibody language","created":"2022-09-26","cited_by_count":2,"area":null},{"id":"2404.01693","title":"HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2405.16206","title":"GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2410.24022","title":"SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation","created":"2024-10-31","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":"2505.20036","title":"Beyond Simple Concatenation: Fairly Assessing PLM Architectures for Multi-Chain Protein-Protein Interactions Prediction","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.20589","title":"Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2602.20449","title":"Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2604.12176","title":"Evaluating Relational Reasoning in LLMs with REL","created":"2026-04-14","cited_by_count":2,"area":"lr"},{"id":"2403.00875","title":"Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions","created":"2024-03-01","cited_by_count":1,"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":"2407.04055","title":"Benchmark on Drug Target Interaction Modeling from a Drug Structure Perspective","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2410.02023","title":"DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2411.08909","title":"Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers","created":"2024-10-29","cited_by_count":1,"area":"ssm"},{"id":"2502.10365","title":"AffinityFlow: Guided Flows for Antibody Affinity Maturation","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2504.06304","title":"Leveraging State Space Models in Long Range Genomics","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.16896","title":"Structure-Aligned Protein Language Model","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2512.00283","title":"BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models","created":"2025-11-29","cited_by_count":1,"area":null},{"id":"2512.12932","title":"Investigating Data Pruning for Pretraining Biological Foundation Models at Scale","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2603.01464","title":"ProtRLSearch: A Multi-Round Multimodal Protein Search Agent with Large Language Models Trained via Reinforcement Learning","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.18571","title":"CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular Localization","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.30963","title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2310.17415","title":"PETA: Evaluating the Impact of Protein Transfer Learning with Sub-word Tokenization on Downstream Applications","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2402.13418","title":"Efficiently Predicting Mutational Effect on Homologous Proteins by Evolution Encoding","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2405.08334","title":"Could Chemical LLMs benefit from Message Passing","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2410.01784","title":"OmniGenBench: Automating Large-scale in-silico Benchmarking for Genomic Foundation Models","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2502.00694","title":"Leveraging Large Language Models to Predict Antibody Biological Activity Against Influenza A Hemagglutinin","created":"2025-02-02","cited_by_count":0,"area":null},{"id":"2503.18551","title":"Discriminative protein sequence modelling with Latent Space Diffusion","created":"2025-03-24","cited_by_count":0,"area":"diffusion"},{"id":"2504.04453","title":"Prot42: a Novel Family of Protein Language Models for Target-aware Protein Binder Generation","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2505.02022","title":"NbBench: Benchmarking Language Models for Comprehensive Nanobody Tasks","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2506.02052","title":"General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2603.00253","title":"CoPeP: Benchmarking Continual Pretraining for Protein Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.07554","title":"ProteinJEPA: Latent prediction improves protein language model pretraining","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.25388","title":"ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.02624","title":"TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2607.08803","title":"TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.06022","title":"EpiBench: Can LLMs Understand Epitopes for Antibody Drug Discovery?","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.07441","title":"TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.38538","title":"ReLaG: A Scalable Framework Generalizing Random Splits to Data with Latent Relations","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}