{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"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":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2211.09117","title":"MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis","created":"2022-11-16","cited_by_count":227},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153},{"id":"2307.08041","title":"Planting a SEED of Vision in Large Language Model","created":"2023-07-16","cited_by_count":140},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118},{"id":"2502.13967","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","created":"2025-02-19","cited_by_count":110},{"id":"2312.03701","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","created":"2023-12-06","cited_by_count":98},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73},{"id":"2501.10064","title":"One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression","created":"2025-01-17","cited_by_count":48},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46},{"id":"2410.21264","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","created":"2024-10-28","cited_by_count":46},{"id":"2405.13698","title":"How to set AdamW's weight decay as you scale model and dataset size","created":"2024-05-22","cited_by_count":43},{"id":"2411.02393","title":"Adaptive Length Image Tokenization via Recurrent Allocation","created":"2024-11-04","cited_by_count":43},{"id":"2410.20502","title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation","created":"2024-10-27","cited_by_count":41},{"id":"2412.13061","title":"VidTok: A Versatile and Open-Source Video Tokenizer","created":"2024-12-17","cited_by_count":35},{"id":"2407.12718","title":"SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow","created":"2024-07-17","cited_by_count":30},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30},{"id":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27},{"id":"2501.05453","title":"An Empirical Study of Autoregressive Pre-training from Videos","created":"2025-01-09","cited_by_count":21},{"id":"2412.16326","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","created":"2024-12-20","cited_by_count":15},{"id":"2412.06774","title":"Visual Lexicon: Rich Image Features in Language Space","created":"2024-12-09","cited_by_count":12}],"next_cursor":null}