{"total":55,"rows":[{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204,"area":null},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2302.01398","title":"The unreasonable effectiveness of few-shot learning for machine translation","created":"2023-02-02","cited_by_count":91,"area":"lr"},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"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":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2206.10012","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","created":"2022-06-20","cited_by_count":35,"area":null},{"id":"2212.10168","title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2302.09650","title":"Scaling Laws for Multilingual Neural Machine Translation","created":"2023-02-19","cited_by_count":27,"area":null},{"id":"2407.11095","title":"DeepGate3: Towards Scalable Circuit Representation Learning","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2202.06387","title":"Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments","created":"2022-02-13","cited_by_count":23,"area":null},{"id":"2212.07530","title":"Causes and Cures for Interference in Multilingual Translation","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2309.01826","title":"One Wide Feedforward is All You Need","created":"2023-09-04","cited_by_count":15,"area":null},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15,"area":null},{"id":"2504.04338","title":"Data Scaling Laws for End-to-End Autonomous Driving","created":"2025-04-06","cited_by_count":15,"area":"driving"},{"id":"2209.13435","title":"Scaling Laws For Deep Learning Based Image Reconstruction","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2406.16605","title":"CLEAR: Can Language Models Really Understand Causal Graphs?","created":"2024-06-24","cited_by_count":14,"area":"lr"},{"id":"2402.02054","title":"Towards Neural Scaling Laws on Graphs","created":"2024-02-03","cited_by_count":13,"area":null},{"id":"2410.22906","title":"From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes","created":"2024-10-30","cited_by_count":11,"area":null},{"id":"2502.07503","title":"Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2504.03036","title":"IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2509.12818","title":"Data Scaling Laws for Radiology Foundation Models","created":"2025-09-16","cited_by_count":5,"area":null},{"id":"2510.03313","title":"Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2210.14593","title":"Scaling Laws Beyond Backpropagation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2211.06348","title":"Striving for data-model efficiency: Identifying data externalities on group performance","created":"2022-11-11","cited_by_count":4,"area":null},{"id":"2305.12057","title":"Accurate Knowledge Distillation with n-best Reranking","created":"2023-05-20","cited_by_count":4,"area":"distill"},{"id":"2408.11243","title":"Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2506.05070","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2510.26622","title":"Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2212.09982","title":"Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2501.12486","title":"The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2504.07598","title":"On Model and Data Scaling for Skeleton-based Self-Supervised Gait Recognition","created":"2025-04-10","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":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2207.12547","title":"The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2402.19267","title":"Robust Guidance for Unsupervised Data Selection: Capturing Perplexing Named Entities for Domain-Specific Machine Translation","created":"2024-02-29","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":"2505.23032","title":"Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.16303","title":"JaParaPat: A Large-Scale Japanese-English Parallel Patent Application Corpus","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2206.13669","title":"Studying Generalization Through Data Averaging","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2502.12372","title":"Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2510.05177","title":"Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2605.07546","title":"On the Invariance and Generality of Neural Scaling Laws","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.17234","title":"Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2609.03533","title":"Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}