{"total":81,"rows":[{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265,"area":null},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2510.21585","title":"REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects","created":"2025-10-24","cited_by_count":80,"area":null},{"id":"2405.17399","title":"Transformers Can Do Arithmetic with the Right Embeddings","created":"2024-05-27","cited_by_count":78,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2312.17482","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","created":"2023-12-29","cited_by_count":34,"area":null},{"id":"2506.10896","title":"BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP","created":"2025-06-12","cited_by_count":28,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21,"area":null},{"id":"2311.08886","title":"CLIMB: Curriculum Learning for Infant-inspired Model Building","created":"2023-11-15","cited_by_count":20,"area":null},{"id":"2404.01847","title":"Accelerating Transformer Pre-training with 2:4 Sparsity","created":"2024-04-02","cited_by_count":19,"area":null},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2408.04220","title":"Diffusion Guided Language Modeling","created":"2024-08-08","cited_by_count":15,"area":"diffusion"},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2402.06617","title":"FaBERT: Pre-training BERT on Persian Blogs","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2407.04358","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2402.00699","title":"PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Software","created":"2024-02-01","cited_by_count":9,"area":null},{"id":"2405.21022","title":"You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2306.01497","title":"Data-Efficient French Language Modeling with CamemBERTa","created":"2023-06-02","cited_by_count":8,"area":null},{"id":"2309.02373","title":"nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources","created":"2023-09-05","cited_by_count":7,"area":null},{"id":"2407.00935","title":"Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining","created":"2024-07-01","cited_by_count":7,"area":null},{"id":"2504.06962","title":"Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation","created":"2025-04-09","cited_by_count":7,"area":null},{"id":"2302.03023","title":"V1T: large-scale mouse V1 response prediction using a Vision Transformer","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2407.08330","title":"HDT: Hierarchical Document Transformer","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2406.06366","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2505.20802","title":"Leaner Transformers: More Heads, Less Depth","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2311.10770","title":"Exponentially Faster Language Modelling","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2406.07696","title":"Sustainable self-supervised learning for speech representations","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2409.04833","title":"Achieving Peak Performance for Large Language Models: A Systematic Review","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2303.16985","title":"Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2305.02386","title":"Approximating CKY with Transformers","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2310.20589","title":"Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2402.17227","title":"Efficient Backpropagation with Variance-Controlled Adaptive Sampling","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2409.03295","title":"N-gram Prediction and Word Difference Representations for Language Modeling","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2410.09637","title":"ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2504.13219","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2505.12789","title":"Enhancing Transformers Through Conditioned Embedded Tokens","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2603.07162","title":"Spectral Conditioning of Attention Improves Transformer Performance","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2311.04799","title":"DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2411.10573","title":"Hysteresis Activation Function for Efficient Inference","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2505.15696","title":"MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2508.17400","title":"Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2510.19493","title":"What is the Best Sequence Length for BABYLM?","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2307.11170","title":"UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2403.19802","title":"Developing Healthcare Language Model Embedding Spaces","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2404.13077","title":"Improving the Capabilities of Large Language Model Based Marketing Analytics Copilots With Semantic Search And Fine-Tuning","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2404.19319","title":"Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget","created":"2024-04-30","cited_by_count":1,"area":"distill"},{"id":"2407.06533","title":"LETS-C: Leveraging Text Embedding for Time Series Classification","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2411.05882","title":"When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2503.11426","title":"Text Compression for Efficient Language Generation","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2505.24452","title":"Stepsize anything: A unified learning rate schedule for budgeted-iteration training","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2510.18745","title":"Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2604.04281","title":"Preservation Is Not Enough for Width Growth: Regime-Sensitive Selection of Dense LM Warm Starts","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2306.10056","title":"Generate to Understand for Representation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2311.04166","title":"Perturbed examples reveal invariances shared by language models","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2503.02534","title":"SAGE-Amine: Generative Amine Design with Multi-Property Optimization for Efficient CO2 Capture","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2510.14614","title":"First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2512.20941","title":"A Multi-fidelity Double-Delta Wing Dataset and Empirical Scaling Laws for GNN-based Aerodynamic Field Surrogate","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.00100","title":"Learning Speech Representations with Variational Predictive Coding","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.04605","title":"RexBERT: Context Specialized Bidirectional Encoders for E-commerce","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.27153","title":"Preconditioned Attention: Enhancing Efficiency in Transformers","created":"2026-03-28","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":"2605.23244","title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2606.03681","title":"Speedrunning Tabular Foundation Model Pretraining","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2609.07086","title":"Conditioned Initialization for Attention","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.32565","title":"Reading Is Not Leaking: Local, Auditable Measurement and Reduction of Inference Exposure from Public Footprints","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}