{"list":"other","total":77,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"1911.04933","title":"Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks","created":"2019-11-12","cited_by_count":618},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539},{"id":"1911.03030","title":"Certified Data Removal from Machine Learning Models","created":"2019-11-08","cited_by_count":535},{"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":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"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":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"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":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"1806.03884","title":"Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis","created":"2018-06-11","cited_by_count":146},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132},{"id":"2307.14430","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","created":"2023-07-26","cited_by_count":121},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2104.12199","title":"Sampling Permutations for Shapley Value Estimation","created":"2021-04-25","cited_by_count":102},{"id":"2306.04141","title":"Art and the science of generative AI: A deeper dive","created":"2023-06-07","cited_by_count":95},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94},{"id":"2310.15393","title":"DoGE: Domain Reweighting with Generalization Estimation","created":"2023-10-23","cited_by_count":90},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"2312.02406","title":"Efficient Online Data Mixing For Language Model Pre-Training","created":"2023-12-05","cited_by_count":77},{"id":"1901.01151","title":"Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision","created":"2019-01-03","cited_by_count":64},{"id":"2206.10013","title":"Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments","created":"2022-06-20","cited_by_count":50},{"id":"2309.08133","title":"Talkin' 'Bout AI Generation: Copyright and the Generative-AI Supply Chain","created":"2023-09-15","cited_by_count":46},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45},{"id":"2010.12082","title":"A Multilinear Sampling Algorithm to Estimate Shapley Values","created":"2020-10-22","cited_by_count":33},{"id":"2305.14822","title":"Can Copyright be Reduced to Privacy?","created":"2023-05-24","cited_by_count":24},{"id":"2005.10084","title":"Context-Aware Learning to Rank with Self-Attention","created":"2020-05-20","cited_by_count":22},{"id":"2406.09408","title":"Data Attribution for Text-to-Image Models by Unlearning Synthesized Images","created":"2024-06-13","cited_by_count":22},{"id":"2409.19998","title":"Do Influence Functions Work on Large Language Models?","created":"2024-09-30","cited_by_count":20},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18},{"id":"2402.08922","title":"The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes","created":"2024-02-14","cited_by_count":16},{"id":"1906.05224","title":"Estimation of the Shapley value by ergodic sampling","created":"2019-06-12","cited_by_count":15},{"id":"2403.17691","title":"Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes","created":"2024-03-26","cited_by_count":10},{"id":"2410.02498","title":"Dynamic Gradient Alignment for Online Data Mixing","created":"2024-10-03","cited_by_count":10},{"id":"2412.00420","title":"TAROT: Targeted Data Selection via Optimal Transport","created":"2024-11-30","cited_by_count":9}],"next_cursor":null}