{"list":"other","total":69,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2311.16863","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","created":"2023-11-28","cited_by_count":191},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138},{"id":"1709.01450","title":"The Devil is in the Tails: Fine-grained Classification in the Wild","created":"2017-09-05","cited_by_count":89},{"id":"1805.08571","title":"On Coresets for Logistic Regression","created":"2018-05-22","cited_by_count":67},{"id":"2010.15581","title":"The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research","created":"2020-10-22","cited_by_count":67},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63},{"id":"2410.23179","title":"Does equivariance matter at scale?","created":"2024-10-30","cited_by_count":52},{"id":"2306.01244","title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","created":"2023-06-02","cited_by_count":44},{"id":"1906.03329","title":"Sparse Variational Inference: Bayesian Coresets from Scratch","created":"2019-06-07","cited_by_count":28},{"id":"2505.09603","title":"DataMIL: Selecting Data for Robot Imitation Learning with Datamodels","created":"2025-05-14","cited_by_count":28},{"id":"2505.17799","title":"A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances","created":"2025-05-23","cited_by_count":28},{"id":"2204.02766","title":"Data-Centric Green AI: An Exploratory Empirical Study","created":"2022-04-06","cited_by_count":25},{"id":"2107.06869","title":"Core-set Sampling for Efficient Neural Architecture Search","created":"2021-07-08","cited_by_count":23},{"id":"2501.16548","title":"From Efficiency Gains to Rebound Effects: The Problem of Jevons' Paradox in AI's Polarized Environmental Debate","created":"2025-01-27","cited_by_count":23},{"id":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22},{"id":"1811.07579","title":"Deep Active Learning with a Neural Architecture Search","created":"2018-11-19","cited_by_count":17},{"id":"2211.05610","title":"BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning","created":"2022-11-10","cited_by_count":17},{"id":"2504.12427","title":"Position: The Most Expensive Part of an LLM should be its Training Data","created":"2025-04-16","cited_by_count":16},{"id":"2203.04706","title":"Data Representativity for Machine Learning and AI Systems","created":"2022-03-09","cited_by_count":15},{"id":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15},{"id":"1508.05243","title":"Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family Mixtures","created":"2015-08-21","cited_by_count":12},{"id":"2309.02065","title":"Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI","created":"2023-09-05","cited_by_count":12},{"id":"2111.03731","title":"Frugal Machine Learning","created":"2021-11-05","cited_by_count":11},{"id":"2503.09829","title":"SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey","created":"2025-03-12","cited_by_count":10},{"id":"2106.12561","title":"Fine-Grained Data Selection for Improved Energy Efficiency of Federated Edge Learning","created":"2021-06-20","cited_by_count":7},{"id":"2311.03615","title":"CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers","created":"2023-11-06","cited_by_count":6},{"id":"2502.01677","title":"Position: AI Scaling: From Up to Down and Out","created":"2025-02-02","cited_by_count":5},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5},{"id":"2502.07732","title":"When Incentives Backfire, Data Stops Being Human","created":"2025-02-11","cited_by_count":4},{"id":"2502.18955","title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset","created":"2025-02-26","cited_by_count":4},{"id":"2507.11690","title":"The Impact of Coreset Selection on Spurious Correlations and Group Robustness","created":"2025-07-15","cited_by_count":4},{"id":"2411.19623","title":"FairDD: Fair Dataset Distillation","created":"2024-11-29","cited_by_count":3},{"id":"2511.01077","title":"AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs","created":"2025-11-02","cited_by_count":3},{"id":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3},{"id":"2505.24279","title":"On the Scaling of Robustness and Effectiveness in Dense Retrieval","created":"2025-05-30","cited_by_count":2},{"id":"2510.09022","title":"The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound","created":"2025-10-10","cited_by_count":2},{"id":"2510.14053","title":"Position: Require Frontier AI Labs To Release Small \"Analog\" Models","created":"2025-10-15","cited_by_count":2},{"id":"2510.18238","title":"Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards","created":"2025-10-21","cited_by_count":2},{"id":"2506.01869","title":"Frugal Machine Learning for Energy-efficient, and Resource-aware Artificial Intelligence","created":"2025-06-02","cited_by_count":1},{"id":"2509.10367","title":"A Discrepancy-Based Perspective on Dataset Condensation","created":"2025-09-12","cited_by_count":1},{"id":"2511.07032","title":"Fair Bayesian Data Selection via Generalized Discrepancy Measures","created":"2025-11-10","cited_by_count":1},{"id":"2602.00056","title":"How Hyper-Datafication Impacts the Sustainability Costs in Frontier AI","created":"2026-01-20","cited_by_count":1}],"next_cursor":null}