{"total":126,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744,"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":"2301.12040","title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts","created":"2023-01-28","cited_by_count":78,"area":null},{"id":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77,"area":null},{"id":"2302.01649","title":"Structure-informed Language Models Are Protein Designers","created":"2023-02-03","cited_by_count":68,"area":null},{"id":"2410.13782","title":"DPLM-2: A Multimodal Diffusion Protein Language Model","created":"2024-10-17","cited_by_count":64,"area":null},{"id":"2401.06199","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","created":"2024-01-11","cited_by_count":50,"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":"2404.11568","title":"On the Scalability of GNNs for Molecular Graphs","created":"2024-04-17","cited_by_count":36,"area":null},{"id":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34,"area":null},{"id":"2406.00735","title":"Full-Atom Peptide Design based on Multi-modal Flow Matching","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2403.00043","title":"RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks","created":"2024-02-29","cited_by_count":33,"area":null},{"id":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29,"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":"2409.06744","title":"ProteinBench: A Holistic Evaluation of Protein Foundation Models","created":"2024-09-10","cited_by_count":25,"area":null},{"id":"2409.04481","title":"Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials","created":"2024-09-06","cited_by_count":24,"area":null},{"id":"2502.07272","title":"GENERator: A Long-Context Generative Genomic Foundation Model","created":"2025-02-11","cited_by_count":22,"area":null},{"id":"2210.07144","title":"Reprogramming Pretrained Language Models for Antibody Sequence Infilling","created":"2022-10-05","cited_by_count":20,"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":"2212.09925","title":"Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC","created":"2022-12-20","cited_by_count":17,"area":null},{"id":"2411.04165","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","created":"2024-11-06","cited_by_count":13,"area":null},{"id":"2301.02120","title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning","created":"2023-01-05","cited_by_count":12,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2504.11454","title":"Elucidating the Design Space of Multimodal Protein Language Models","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2504.13075","title":"An All-Atom Generative Model for Designing Protein Complexes","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2411.18463","title":"Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2402.10516","title":"Generative AI for Controllable Protein Sequence Design: A Survey","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2505.22869","title":"CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models","created":"2025-05-28","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":"2307.06797","title":"Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2308.16259","title":"Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction","created":"2023-08-30","cited_by_count":7,"area":null},{"id":"2403.12995","title":"ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2406.05347","title":"MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2504.10917","title":"Towards A Universal Graph Structural Encoder","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2509.07983","title":"Steering Protein Language Models","created":"2025-07-01","cited_by_count":7,"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":"2503.04490","title":"Large Language Models in Bioinformatics: A Survey","created":"2025-03-06","cited_by_count":6,"area":null},{"id":"2301.00004","title":"SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering","created":"2022-12-29","cited_by_count":5,"area":null},{"id":"2301.02748","title":"Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model","created":"2023-01-06","cited_by_count":5,"area":null},{"id":"2306.01824","title":"Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2407.07443","title":"Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph Diffusion","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2501.15007","title":"Controllable Protein Sequence Generation with LLM Preference Optimization","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2505.18966","title":"Protein Design with Dynamic Protein Vocabulary","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2505.20346","title":"PDFBench: A Benchmark for De novo Protein Design from Function","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2506.03028","title":"Protein Inverse Folding From Structure Feedback","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2211.10422","title":"Forecasting labels under distribution-shift for machine-guided sequence design","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2311.05363","title":"Beyond the training set: an intuitive method for detecting distribution shift in model-based optimization","created":"2023-11-09","cited_by_count":4,"area":null},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2506.04235","title":"AbBiBench: A Benchmark for Antibody Binding Affinity Maturation and Design","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.08954","title":"Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction","created":"2025-06-10","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":"2301.13154","title":"Protein Representation Learning via Knowledge Enhanced Primary Structure Modeling","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2304.08299","title":"Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2401.06173","title":"Tree Search-Based Evolutionary Bandits for Protein Sequence Optimization","created":"2024-01-08","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":"2404.09738","title":"AMPCliff: quantitative definition and benchmarking of activity cliffs in antimicrobial peptides","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2405.18749","title":"A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2505.20052","title":"Ankh3: Multi-Task Pretraining with Sequence Denoising and Completion Enhances Protein Representations","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2508.17345","title":"ShortListing Model: A Streamlined SimplexDiffusion for Discrete Variable Generation","created":"2025-08-24","cited_by_count":3,"area":null},{"id":"2606.16905","title":"Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences","created":"2026-06-15","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":"2306.00872","title":"Is novelty predictable?","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2411.15215","title":"S$^2$ALM: Sequence-Structure Pre-trained Large Language Model for Comprehensive Antibody Representation Learning","created":"2024-11-20","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":"2506.09332","title":"InstructPro: Natural Language Guided Ligand-Binding Protein Design","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2602.21750","title":"From Words to Amino Acids: Does the Curse of Depth Persist?","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.04045","title":"Inference-Time Toxicity Mitigation in Protein Language Models","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.04736","title":"Distribution-Conditioned Transport","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.06740","title":"ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2303.16452","title":"ProtFIM: Fill-in-Middle Protein Sequence Design via Protein Language Models","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2305.01941","title":"Exploring the Protein Sequence Space with Global Generative Models","created":"2023-05-03","cited_by_count":1,"area":null},{"id":"2306.04899","title":"Multi-level Protein Representation Learning for Blind Mutational Effect Prediction","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2311.02333","title":"Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision","created":"2023-11-04","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":"2410.11499","title":"BSM: Small but Powerful Biological Sequence Model for Genes and Proteins","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2504.17068","title":"In-Context Learning can distort the relationship between sequence likelihoods and biological fitness","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2505.11610","title":"Foundation Models for AI-Enabled Biological Design","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2507.13646","title":"A Comprehensive Review of Transformer-based language models for Protein Sequence Analysis and Design","created":"2025-07-18","cited_by_count":1,"area":null},{"id":"2509.18153","title":"A deep reinforcement learning platform for antibiotic discovery","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2603.26378","title":"Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards","created":"2026-03-27","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":"2609.03377","title":"SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.14011","title":"Convergent Emergence of In-Context Learning Across Modalities","created":"2026-09-12","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":"2312.00842","title":"ESM-NBR: fast and accurate nucleic acid-binding residue prediction via protein language model feature representation and multi-task learning","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2407.16375","title":"Ranking protein-protein models with large language models and graph neural networks","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2409.10579","title":"Recent advances in deep learning and language models for studying the microbiome","created":"2024-09-15","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":"2410.21069","title":"EMOCPD: Efficient Attention-based Models for Computational Protein Design Using Amino Acid Microenvironment","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2410.21283","title":"pLDDT-Predictor: High-speed Protein Screening Using Transformer and ESM2","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2411.02109","title":"One protein is all you need","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2411.05966","title":"Energy Efficient Protein Language Models: Leveraging Small Language Models with LoRA for Controllable Protein Generation","created":"2024-11-08","cited_by_count":0,"area":null},{"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":"2504.08437","title":"Customizing Spider Silk: Generative Models with Mechanical Property Conditioning for Protein Engineering","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2506.14853","title":"DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing","created":"2025-06-17","cited_by_count":0,"area":null}],"next_cursor":"100"}