{"total":34,"rows":[{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555,"area":null},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236,"area":null},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2202.08384","title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","created":"2022-02-17","cited_by_count":63,"area":null},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"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":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36,"area":null},{"id":"2402.10430","title":"Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models","created":"2024-02-16","cited_by_count":32,"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":"2109.05897","title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2203.04071","title":"AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch","created":"2022-03-08","cited_by_count":11,"area":null},{"id":"2410.07041","title":"Emergent properties with repeated examples","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2306.08590","title":"Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2207.13988","title":"Sequence to sequence pretraining for a less-resourced Slovenian language","created":"2022-07-28","cited_by_count":9,"area":null},{"id":"2212.08390","title":"Lessons learned from the evaluation of Spanish Language Models","created":"2022-12-16","cited_by_count":8,"area":null},{"id":"2408.15300","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2312.00567","title":"Explanatory Argument Extraction of Correct Answers in Resident Medical Exams","created":"2023-12-01","cited_by_count":6,"area":null},{"id":"2601.21698","title":"Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2306.02294","title":"Exposing Bias in Online Communities through Large-Scale Language Models","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2606.24998","title":"Internal Data Repetition Destroys Language Models","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2311.09271","title":"An Empathetic User-Centric Chatbot for Emotional Support","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2602.03980","title":"Transformers perform adaptive partial pooling","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2407.01607","title":"Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2507.10613","title":"Sub-Scaling Laws: On the Role of Data Density and Training Strategies in LLMs","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2107.14796","title":"Data-driven modeling of time-domain induced polarization","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2408.09218","title":"FQGA-single: Towards Fewer Training Epochs and Fewer Model Parameters for Image-to-Image Translation Tasks","created":"2024-08-17","cited_by_count":0,"area":null}],"next_cursor":null}