{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"1908.08619","title":"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms","created":"2019-08-22","cited_by_count":148},{"id":"1909.11671","title":"Data Valuation using Reinforcement Learning","created":"2019-09-25","cited_by_count":116},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"1805.08125","title":"A Marketplace for Data: An Algorithmic Solution","created":"2018-05-21","cited_by_count":76},{"id":"1306.4265","title":"Bounding the Estimation Error of Sampling-based Shapley Value Approximation","created":"2013-06-18","cited_by_count":58},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38},{"id":"1805.11450","title":"Model-based Pricing for Machine Learning in a Data Marketplace","created":"2018-05-26","cited_by_count":37},{"id":"2208.12354","title":"Fundamentals of Task-Agnostic Data Valuation","created":"2022-08-25","cited_by_count":19},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17},{"id":"2210.08723","title":"Private Data Valuation and Fair Payment in Data Marketplaces","created":"2022-10-17","cited_by_count":14},{"id":"2306.02071","title":"DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation","created":"2023-06-03","cited_by_count":12},{"id":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11},{"id":"2503.07661","title":"Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy","created":"2025-03-08","cited_by_count":11},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7},{"id":"2508.16082","title":"On Task Vectors and Gradients","created":"2025-08-22","cited_by_count":7},{"id":"2402.01943","title":"Precedence-Constrained Winter Value for Effective Graph Data Valuation","created":"2024-02-02","cited_by_count":6},{"id":"2509.01548","title":"Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing","created":"2025-09-01","cited_by_count":6},{"id":"2405.17489","title":"On the Inflation of KNN-Shapley Value","created":"2024-05-25","cited_by_count":4},{"id":"2406.11730","title":"CHG Shapley: Efficient Data Valuation and Selection towards Trustworthy Machine Learning","created":"2024-06-17","cited_by_count":4},{"id":"2510.14163","title":"Towards Reversible Model Merging For Low-rank Weights","created":"2025-10-15","cited_by_count":3},{"id":"2406.04257","title":"Data Measurements for Decentralized Data Markets","created":"2024-06-06","cited_by_count":2},{"id":"2408.12659","title":"Disentangled Structural and Featural Representation for Task-Agnostic Graph Valuation","created":"2024-08-22","cited_by_count":2},{"id":"2509.15651","title":"Toward Efficient Influence Function: Dropout as a Compression Tool","created":"2025-09-19","cited_by_count":2},{"id":"2511.11851","title":"Defending Unauthorized Model Merging via Dual-Stage Weight Protection","created":"2025-11-14","cited_by_count":2},{"id":"2310.02373","title":"SelectFormer: Private and Practical Data Selection for Transformers","created":"2023-10-03","cited_by_count":1},{"id":"2411.00745","title":"Private, Augmentation-Robust and Task-Agnostic Data Valuation Approach for Data Marketplace","created":"2024-11-01","cited_by_count":1},{"id":"2412.07688","title":"A Joint Energy and Differentially-Private Smart Meter Data Market","created":"2024-12-10","cited_by_count":1}],"next_cursor":null}