{"list":"other","total":57,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"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":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2604.14148","title":"Seedance 2.0: Advancing Video Generation for World Complexity","created":"2026-04-15","cited_by_count":160},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"1811.09245","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","created":"2018-11-22","cited_by_count":120},{"id":"2502.14831","title":"Improving the Diffusability of Autoencoders","created":"2025-02-20","cited_by_count":80},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76},{"id":"2405.20279","title":"CV-VAE: A Compatible Video VAE for Latent Generative Video Models","created":"2024-05-30","cited_by_count":70},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58},{"id":"2411.17459","title":"WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model","created":"2024-11-26","cited_by_count":57},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53},{"id":"2012.03448","title":"Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems","created":"2020-12-07","cited_by_count":50},{"id":"2411.06449","title":"Improved Video VAE for Latent Video Diffusion Model","created":"2024-11-10","cited_by_count":48},{"id":"2403.14148","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","created":"2024-03-21","cited_by_count":42},{"id":"2409.01199","title":"OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model","created":"2024-09-02","cited_by_count":30},{"id":"2512.13687","title":"Towards Scalable Pre-training of Visual Tokenizers for Generation","created":"2025-12-15","cited_by_count":28},{"id":"2403.12042","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","created":"2024-03-18","cited_by_count":27},{"id":"2405.14477","title":"LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models","created":"2024-05-23","cited_by_count":22},{"id":"2512.17909","title":"Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing","created":"2025-12-19","cited_by_count":22},{"id":"2507.15856","title":"Latent Denoising Makes Good Tokenizers","created":"2025-07-21","cited_by_count":20},{"id":"2503.14325","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","created":"2025-03-18","cited_by_count":17},{"id":"2502.07001","title":"From Image to Video: An Empirical Study of Diffusion Representations","created":"2025-02-10","cited_by_count":15},{"id":"2412.17726","title":"VidTwin: Video VAE with Decoupled Structure and Dynamics","created":"2024-12-23","cited_by_count":14},{"id":"2504.10567","title":"H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models","created":"2025-04-14","cited_by_count":13},{"id":"2512.05394","title":"Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability","created":"2025-12-05","cited_by_count":11},{"id":"2511.14530","title":"DeCo-VAE: Learning Compact Latents for Video Reconstruction via Decoupled Representation","created":"2025-11-18","cited_by_count":4},{"id":"2512.13421","title":"RecTok: Reconstruction Distillation along Rectified Flow","created":"2025-12-15","cited_by_count":4}],"next_cursor":null}