{"list":"other","total":65,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2001.02908","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","created":"2020-01-09","cited_by_count":180},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114},{"id":"1811.02307","title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","created":"2018-11-06","cited_by_count":102},{"id":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94},{"id":"2502.09509","title":"EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling","created":"2025-02-13","cited_by_count":89},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78},{"id":"1911.06978","title":"Grounding Human-to-Vehicle Advice for Self-driving Vehicles","created":"2019-11-16","cited_by_count":71},{"id":"2012.03448","title":"Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems","created":"2020-12-07","cited_by_count":50},{"id":"2410.20280","title":"MarDini: Masked Autoregressive Diffusion for Video Generation at Scale","created":"2024-10-26","cited_by_count":49},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45},{"id":"2412.09607","title":"Spectral Image Tokenizer","created":"2024-12-12","cited_by_count":15},{"id":"2411.16681","title":"Factorized Visual Tokenization and Generation","created":"2024-11-25","cited_by_count":11},{"id":"1805.07813","title":"Learning Real-World Robot Policies by Dreaming","created":"2018-05-20","cited_by_count":10},{"id":"2504.02515","title":"Exploration-Driven Generative Interactive Environments","created":"2025-04-03","cited_by_count":9}],"next_cursor":null}