{"total":184,"rows":[{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528,"area":null},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523,"area":null},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363,"area":null},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303,"area":null},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159,"area":null},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"area":null},{"id":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144,"area":null},{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138,"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":"2210.16859","title":"A Solvable Model of Neural Scaling Laws","created":"2022-10-30","cited_by_count":116,"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":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"area":null},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98,"area":null},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2102.04074","title":"Learning Curve Theory","created":"2021-02-08","cited_by_count":85,"area":null},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2103.10948","title":"The Shape of Learning Curves: a Review","created":"2021-03-19","cited_by_count":70,"area":null},{"id":"2104.03113","title":"Scaling Scaling Laws with Board Games","created":"2021-04-07","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":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"area":null},{"id":"2410.23179","title":"Does equivariance matter at scale?","created":"2024-10-30","cited_by_count":52,"area":null},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2303.13824","title":"$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference","created":"2023-03-24","cited_by_count":47,"area":null},{"id":"2206.04664","title":"On Data Scaling in Masked Image Modeling","created":"2022-06-09","cited_by_count":46,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2410.16377","title":"A Simple Model of Inference Scaling Laws","created":"2024-10-21","cited_by_count":36,"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":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2507.11783","title":"EEG Foundation Models: A Critical Review of Current Progress and Future Directions","created":"2025-07-15","cited_by_count":32,"area":null},{"id":"2411.06646","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","created":"2024-11-11","cited_by_count":30,"area":null},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2302.09650","title":"Scaling Laws for Multilingual Neural Machine Translation","created":"2023-02-19","cited_by_count":27,"area":null},{"id":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","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":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2412.06540","title":"Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2505.19227","title":"Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law","created":"2025-05-25","cited_by_count":24,"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":"2207.01725","title":"How Much More Data Do I Need? Estimating Requirements for Downstream Tasks","created":"2022-07-04","cited_by_count":23,"area":null},{"id":"2502.06905","title":"Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty","created":"2025-02-10","cited_by_count":22,"area":null},{"id":"2205.12676","title":"Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2201.12655","title":"Error Scaling Laws for Kernel Classification under Source and Capacity Conditions","created":"2022-01-29","cited_by_count":17,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2405.16684","title":"gzip Predicts Data-dependent Scaling Laws","created":"2024-05-26","cited_by_count":16,"area":null},{"id":"2510.05197","title":"Efficient Prediction of Pass@k Scaling in Large Language Models","created":"2025-10-06","cited_by_count":16,"area":null},{"id":"2108.11018","title":"A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?","created":"2021-08-25","cited_by_count":15,"area":null},{"id":"2210.01234","title":"Optimizing Data Collection for Machine Learning","created":"2022-10-03","cited_by_count":15,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2412.07942","title":"Neural Scaling Laws Rooted in the Data Distribution","created":"2024-12-10","cited_by_count":15,"area":null},{"id":"2209.13435","title":"Scaling Laws For Deep Learning Based Image Reconstruction","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2402.02054","title":"Towards Neural Scaling Laws on Graphs","created":"2024-02-03","cited_by_count":13,"area":null},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2102.00940","title":"Meta-learning with negative learning rates","created":"2021-02-01","cited_by_count":11,"area":null},{"id":"2302.06960","title":"Data pruning and neural scaling laws: fundamental limitations of score-based algorithms","created":"2023-02-14","cited_by_count":11,"area":null},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2306.11475","title":"Delegated Classification","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2405.20456","title":"Scaling Laws for the Value of Individual Data Points in Machine Learning","created":"2024-05-30","cited_by_count":10,"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":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2103.09108","title":"Is it enough to optimize CNN architectures on ImageNet?","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2106.03485","title":"Redundant representations help generalization in wide neural networks","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2303.05420","title":"Kernel Regression with Infinite-Width Neural Networks on Millions of Examples","created":"2023-03-09","cited_by_count":9,"area":null},{"id":"2312.07779","title":"Tell, don't show: Declarative facts influence how LLMs generalize","created":"2023-12-12","cited_by_count":9,"area":null},{"id":"2408.16947","title":"An Empirical Study of Scaling Laws for Transfer","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2502.21009","title":"Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2504.08842","title":"Towards Combinatorial Interpretability of Neural Computation","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2406.09366","title":"Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations","created":"2024-06-13","cited_by_count":8,"area":null},{"id":"2404.05579","title":"DRoP: Distributionally Robust Data Pruning","created":"2024-04-08","cited_by_count":7,"area":null},{"id":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2412.07585","title":"Scaling Sequential Recommendation Models with Transformers","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2211.08430","title":"Power-law Scaling to Assist with Key Challenges in Artificial Intelligence","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2302.03068","title":"Evaluating Self-Supervised Learning via Risk Decomposition","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2304.06875","title":"nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales","created":"2023-04-14","cited_by_count":6,"area":null},{"id":"2311.09480","title":"Show Your Work with Confidence: Confidence Bands for Tuning Curves","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2409.06821","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null}],"next_cursor":"100"}