{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"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":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2301.11093","title":"Simple diffusion: End-to-end diffusion for high resolution images","created":"2023-01-26","cited_by_count":422},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","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":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2411.00776","title":"Randomized Autoregressive Visual Generation","created":"2024-11-01","cited_by_count":127},{"id":"2409.16211","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","created":"2024-09-24","cited_by_count":98},{"id":"2412.15205","title":"FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching","created":"2024-12-19","cited_by_count":80},{"id":"2502.20388","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","created":"2025-02-27","cited_by_count":71},{"id":"1806.07772","title":"Accurate and Diverse Sampling of Sequences based on a \"Best of Many\" Sample Objective","created":"2018-06-20","cited_by_count":56},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56},{"id":"2501.07730","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","created":"2025-01-13","cited_by_count":50},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45},{"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":"2406.19320","title":"Efficient World Models with Context-Aware Tokenization","created":"2024-06-27","cited_by_count":33},{"id":"2503.10772","title":"FlowTok: Flowing Seamlessly Across Text and Image Tokens","created":"2025-03-13","cited_by_count":33},{"id":"2412.18653","title":"1.58-bit FLUX","created":"2024-12-24","cited_by_count":31},{"id":"2505.17011","title":"Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space","created":"2025-05-22","cited_by_count":16},{"id":"2505.14687","title":"Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers","created":"2025-05-20","cited_by_count":13},{"id":"2007.01738","title":"Video Prediction via Example Guidance","created":"2020-07-03","cited_by_count":9},{"id":"2503.14494","title":"Deeply Supervised Flow-Based Generative Models","created":"2025-03-18","cited_by_count":9},{"id":"2602.09024","title":"Autoregressive Image Generation with Masked Bit Modeling","created":"2026-02-09","cited_by_count":9},{"id":"2507.13942","title":"Frozen Forecasting: A Unified Evaluation","created":"2025-07-18","cited_by_count":4},{"id":"2507.02862","title":"RefTok: Reference-Based Tokenization for Video Generation","created":"2025-07-03","cited_by_count":2}],"next_cursor":null}