{"total":125,"rows":[{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113,"area":null},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112,"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":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2404.03828","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","created":"2024-04-04","cited_by_count":38,"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":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30,"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":"2406.12723","title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","created":"2024-06-18","cited_by_count":24,"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":"2411.02796","title":"Specialized Foundation Models Struggle to Beat Supervised Baselines","created":"2024-11-05","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":"2404.03830","title":"BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model","created":"2024-04-04","cited_by_count":21,"area":null},{"id":"2407.11435","title":"Genomic Language Models: Opportunities and Challenges","created":"2024-07-16","cited_by_count":20,"area":null},{"id":"2410.23126","title":"Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes","created":"2024-10-30","cited_by_count":19,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2405.10812","title":"VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling","created":"2024-05-13","cited_by_count":15,"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":"2411.06518","title":"Causal Representation Learning from Multimodal Biomedical Observations","created":"2024-11-10","cited_by_count":13,"area":null},{"id":"2412.13716","title":"Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2410.02143","title":"Plug-and-Play Controllable Generation for Discrete Masked Models","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2406.01627","title":"GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models","created":"2024-06-01","cited_by_count":10,"area":null},{"id":"2410.12459","title":"HELM: Hierarchical Encoding for mRNA Language Modeling","created":"2024-10-16","cited_by_count":10,"area":null},{"id":"2412.19191","title":"Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models","created":"2024-12-26","cited_by_count":10,"area":null},{"id":"2602.17162","title":"JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures","created":"2026-02-19","cited_by_count":9,"area":null},{"id":"2401.02789","title":"Large Language Models in Plant Biology","created":"2024-01-05","cited_by_count":8,"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":"2406.14150","title":"Multi-modal Transfer Learning between Biological Foundation Models","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2502.10807","title":"HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model","created":"2025-02-15","cited_by_count":7,"area":null},{"id":"2411.02125","title":"Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2412.05430","title":"DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA","created":"2024-12-06","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":"2602.18858","title":"Hyperbolic Busemann Neural Networks","created":"2026-02-21","cited_by_count":5,"area":null},{"id":"2310.07644","title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2406.13133","title":"PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation Model","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2505.19531","title":"Minimalist Softmax Attention Provably Learns Constrained Boolean Functions","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2511.11758","title":"Protein Structure Tokenization via Geometric Byte Pair Encoding","created":"2025-11-13","cited_by_count":4,"area":null},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2410.16212","title":"Comprehensive benchmarking of large language models for RNA secondary structure prediction","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2412.10347","title":"COMET: Benchmark for Comprehensive Biological Multi-omics Evaluation Tasks and Language Models","created":"2024-12-13","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":"2502.18405","title":"Enhancing DNA Foundation Models to Address Masking Inefficiencies","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2507.05265","title":"BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2509.21650","title":"Understanding and Enhancing Mask-Based Pretraining towards Universal Representations","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2602.10603","title":"dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2602.23981","title":"Intrinsic Lorentz Neural Network","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2401.00642","title":"Predicting Anti-microbial Resistance using Large Language Models","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2402.16901","title":"FGBERT: Function-Driven Pre-trained Gene Language Model for Metagenomics","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2406.00164","title":"DYNA: Disease-Specific Language Model for Variant Pathogenicity","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2407.16940","title":"GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning","created":"2024-07-24","cited_by_count":2,"area":null},{"id":"2412.18827","title":"PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2502.07299","title":"Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2503.16565","title":"Gene42: Long-Range Genomic Foundation Model With Dense Attention","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2508.04441","title":"Benchmarking Foundation Models for Mitotic Figure Classification","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2606.07607","title":"Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability Methods","created":"2026-05-29","cited_by_count":2,"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":"2311.02401","title":"BarcodeBERT: Transformers for Biodiversity Analysis","created":"2023-11-04","cited_by_count":1,"area":null},{"id":"2311.16157","title":"GeoTop: Advancing Image Classification with Geometric-Topological Analysis","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2312.17372","title":"Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2402.08777","title":"DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2405.05998","title":"Whole Genome Transformer for Gene Interaction Effects in Microbiome Habitat Specificity","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2409.19788","title":"Exploring Adversarial Robustness in Classification tasks using DNA Language Models","created":"2024-09-29","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":"2412.04075","title":"Does your model understand genes? A benchmark of gene properties for biological and text models","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2412.07201","title":"A Review on the Applications of Transformer-based language models for Nucleotide Sequence Analysis","created":"2024-12-10","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":"2505.02206","title":"DNAZEN: Enhanced Gene Sequence Representations via Mixed Granularities of Coding Units","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2506.18940","title":"eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2507.16978","title":"Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2507.18570","title":"Hybrid Tokenization Strategy for DNA Language Model using Byte Pair Encoding and K-MER Methods","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2507.19523","title":"Language Models for Controllable DNA Sequence Design","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2508.15103","title":"Equi-mRNA: Protein Translation Equivariant Encoding for mRNA Language Models","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2509.12266","title":"Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models","created":"2025-09-13","cited_by_count":1,"area":null},{"id":"2509.18529","title":"Reverse-Complement Consistency for DNA Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2509.26116","title":"UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binning","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.07706","title":"Large Language Models Meet Virtual Cell: A Survey","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2510.27629","title":"Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models","created":"2025-10-31","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":"2603.06950","title":"How Private Are DNA Embeddings? Inverting Foundation Model Representations of Genomic Sequences","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.08913","title":"Quantifying Memorization and Privacy Risks in Genomic Language Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.21690","title":"Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.13713","title":"CisTransCell: Single-Cell Perturbation Prediction via Gene Function, Regulatory Control, and Cellular Context","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2307.10634","title":"Generative Language Models on Nucleotide Sequences of Human Genes","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2309.11087","title":"Embed-Search-Align: DNA Sequence Alignment using Transformer Models","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2310.08738","title":"Splicing Up Your Predictions with RNA Contrastive Learning","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2402.08075","title":"Efficient and Scalable Fine-Tune of Language Models for Genome Understanding","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2405.09585","title":"An Embarrassingly Simple Approach to Enhance Transformer Performance in Genomic Selection for Crop Breeding","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2405.11461","title":"DocReLM: Mastering Document Retrieval with Language Model","created":"2024-05-19","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":"2411.03522","title":"Exploring the Potentials and Challenges of Using Large Language Models for the Analysis of Transcriptional Regulation of Long Non-coding RNAs","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2502.01311","title":"TFBS-Finder: Deep Learning-based Model with DNABERT and Convolutional Networks to Predict Transcription Factor Binding Sites","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2503.04413","title":"Can Large Language Models Predict Antimicrobial Resistance Gene?","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2503.10655","title":"Language modelling techniques for analysing the impact of human genetic variation","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2506.02212","title":"Leveraging Natural Language Processing to Unravel the Mystery of Life: A Review of NLP Approaches in Genomics, Transcriptomics, and Proteomics","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.10271","title":"Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2507.09378","title":"Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2507.15087","title":"Evaluation of Coding Schemes for Transformer-based Gene Sequence Modeling","created":"2025-07-20","cited_by_count":0,"area":null}],"next_cursor":"100"}