{"list":"other","total":52,"rows":[{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"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":"2301.11093","title":"Simple diffusion: End-to-end diffusion for high resolution images","created":"2023-01-26","cited_by_count":422},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2104.03602","title":"SiT: Self-supervised vIsion Transformer","created":"2021-04-08","cited_by_count":99},{"id":"2412.15205","title":"FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching","created":"2024-12-19","cited_by_count":80},{"id":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"2312.03626","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","created":"2023-12-06","cited_by_count":40},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","cited_by_count":32},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26},{"id":"2405.16418","title":"Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective","created":"2024-05-26","cited_by_count":24},{"id":"2406.05871","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","created":"2024-06-09","cited_by_count":24},{"id":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","cited_by_count":23},{"id":"2412.15579","title":"Score-based Generative Diffusion Models for Social Recommendations","created":"2024-12-20","cited_by_count":23},{"id":"2402.09469","title":"Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs","created":"2024-02-12","cited_by_count":22},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22},{"id":"2411.17522","title":"On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality","created":"2024-11-26","cited_by_count":22},{"id":"2412.06148","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","created":"2024-12-09","cited_by_count":21},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19},{"id":"2405.03251","title":"Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond","created":"2024-05-06","cited_by_count":15},{"id":"2502.00688","title":"High-Order Matching for One-Step Shortcut Diffusion Models","created":"2025-02-02","cited_by_count":15},{"id":"2501.04377","title":"On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis","created":"2025-01-08","cited_by_count":14},{"id":"2501.06444","title":"On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective","created":"2025-01-11","cited_by_count":14},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13},{"id":"2412.18040","title":"Theoretical Constraints on the Expressive Power of $\\mathsf{RoPE}$-based Tensor Attention Transformers","created":"2024-12-23","cited_by_count":12},{"id":"2502.08150","title":"Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling","created":"2025-02-12","cited_by_count":12},{"id":"2502.00500","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","created":"2025-02-01","cited_by_count":11},{"id":"2501.04299","title":"Circuit Complexity Bounds for Visual Autoregressive Model","created":"2025-01-08","cited_by_count":10},{"id":"2502.06167","title":"Universal Approximation of Visual Autoregressive Transformers","created":"2025-02-10","cited_by_count":9},{"id":"2208.03367","title":"Sublinear Time Algorithm for Online Weighted Bipartite Matching","created":"2022-08-05","cited_by_count":7},{"id":"2305.08353","title":"Fast and Efficient Matching Algorithm with Deadline Instances","created":"2023-05-15","cited_by_count":7},{"id":"2501.09982","title":"RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation","created":"2025-01-17","cited_by_count":6}],"next_cursor":null}