{"total":157,"rows":[{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216,"area":null},{"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":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91,"area":null},{"id":"2405.03162","title":"Advancing Multimodal Medical Capabilities of Gemini","created":"2024-05-06","cited_by_count":90,"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":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59,"area":null},{"id":"2409.11654","title":"How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities","created":"2024-09-18","cited_by_count":57,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2311.11483","title":"A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records","created":"2023-11-20","cited_by_count":31,"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":"2311.12570","title":"BEND: Benchmarking DNA Language Models on biologically meaningful tasks","created":"2023-11-21","cited_by_count":29,"area":null},{"id":"2405.20131","title":"Language Models Need Inductive Biases to Count Inductively","created":"2024-05-30","cited_by_count":25,"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":"2402.19155","title":"Beyond Language Models: Byte Models are Digital World Simulators","created":"2024-02-29","cited_by_count":22,"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":"2407.11435","title":"Genomic Language Models: Opportunities and Challenges","created":"2024-07-16","cited_by_count":20,"area":null},{"id":"2307.14397","title":"A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot","created":"2023-07-26","cited_by_count":19,"area":null},{"id":"2401.13536","title":"Finetuning Foundation Models for Joint Analysis Optimization","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2405.17537","title":"CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale","created":"2024-05-27","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":"2411.04165","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":"2411.06518","title":"Causal Representation Learning from Multimodal Biomedical Observations","created":"2024-11-10","cited_by_count":13,"area":null},{"id":"2412.08174","title":"Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?","created":"2024-12-11","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":"2409.09825","title":"GP-GPT: Large Language Model for Gene-Phenotype Mapping","created":"2024-09-15","cited_by_count":11,"area":null},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"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":"2402.16014","title":"OmniArch: Building Foundation Model For Scientific Computing","created":"2024-02-25","cited_by_count":9,"area":null},{"id":"2402.16714","title":"Quantum Transformer: Accelerating model inference via quantum linear algebra","created":"2024-02-26","cited_by_count":9,"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":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2310.02713","title":"scHyena: Foundation Model for Full-Length Single-Cell RNA-Seq Analysis in Brain","created":"2023-10-04","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":"2403.17978","title":"Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection","created":"2024-03-23","cited_by_count":6,"area":null},{"id":"2405.19036","title":"State Space Models are Provably Comparable to Transformers in Dynamic Token Selection","created":"2024-05-29","cited_by_count":6,"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":"2503.04490","title":"Large Language Models in Bioinformatics: A Survey","created":"2025-03-06","cited_by_count":6,"area":null},{"id":"2503.07981","title":"Regulatory DNA sequence Design with Reinforcement Learning","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2406.09003","title":"Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2505.20578","title":"Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.01833","title":"SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2603.05193","title":"Transducing Language Models","created":"2026-03-05","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":"2410.19236","title":"SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2502.13991","title":"Learning to Discover Regulatory Elements for Gene Expression Prediction","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2505.18150","title":"Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learning","created":"2025-05-23","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":"2403.01628","title":"Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium","created":"2024-03-03","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":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","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":"2502.01330","title":"Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2502.18538","title":"Revisiting Convolution Architecture in the Realm of DNA Foundation Models","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2507.21648","title":"Hyperbolic Genome Embeddings","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2508.06587","title":"Hypergraph Neural Network with State Space Models for Node Classification","created":"2025-08-08","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":"2402.16901","title":"FGBERT: Function-Driven Pre-trained Gene Language Model for Metagenomics","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2402.17779","title":"Assessing the importance of long-range correlations for deep-learning-based sleep staging","created":"2024-02-22","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":"2408.07180","title":"Unlocking Efficiency: Adaptive Masking for Gene Transformer Models","created":"2024-08-13","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":"2503.03773","title":"A Phylogenetic Approach to Genomic Language Modeling","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","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":"2505.10983","title":"GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2512.23824","title":"MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling","created":"2025-12-29","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":"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":"2409.15697","title":"dnaGrinder: a lightweight and high-capacity genomic foundation model","created":"2024-09-24","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":"2412.07201","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":"2502.01659","title":"Longer Attention Span: Increasing Transformer Context Length with Sparse Graph Processing Techniques","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2502.07616","title":"Tractable Transformers for Flexible Conditional Generation","created":"2025-02-11","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":"2504.07619","title":"Beating Transformers using Synthetic Cognition","created":"2025-04-10","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":"2505.08918","title":"When repeats drive the vocabulary: a Byte-Pair Encoding analysis of T2T primate genomes","created":"2025-05-13","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":"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":"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}],"next_cursor":"100"}