{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304},{"id":"2303.14389","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","created":"2023-03-25","cited_by_count":262},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195},{"id":"2202.10261","title":"A Self-Supervised Descriptor for Image Copy Detection","created":"2022-02-21","cited_by_count":176},{"id":"2307.08698","title":"Flow Matching in Latent Space","created":"2023-07-17","cited_by_count":160},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103},{"id":"2407.21720","title":"Detecting, Explaining, and Mitigating Memorization in Diffusion Models","created":"2024-07-31","cited_by_count":95},{"id":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66},{"id":"2307.03694","title":"Scalable Membership Inference Attacks via Quantile Regression","created":"2023-07-07","cited_by_count":65},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50},{"id":"2408.01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","created":"2024-08-02","cited_by_count":42},{"id":"2406.02366","title":"Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models","created":"2024-06-04","cited_by_count":37},{"id":"2209.09024","title":"Dataset Inference for Self-Supervised Models","created":"2022-09-16","cited_by_count":36},{"id":"2406.09416","title":"Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization","created":"2024-06-13","cited_by_count":36},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32},{"id":"2205.07890","title":"On the Difficulty of Defending Self-Supervised Learning against Model Extraction","created":"2022-05-16","cited_by_count":22},{"id":"2409.13745","title":"Context-Aware Membership Inference Attacks against Pre-trained Large Language Models","created":"2024-09-11","cited_by_count":22},{"id":"2401.12233","title":"Memorization in Self-Supervised Learning Improves Downstream Generalization","created":"2024-01-19","cited_by_count":18},{"id":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","cited_by_count":11},{"id":"2409.19069","title":"Localizing Memorization in SSL Vision Encoders","created":"2024-09-27","cited_by_count":9}],"next_cursor":null}