{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"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":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"1910.05449","title":"MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction","created":"2019-10-12","cited_by_count":420},{"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":"2007.13732","title":"Learning Lane Graph Representations for Motion Forecasting","created":"2020-07-27","cited_by_count":382},{"id":"2311.12198","title":"PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics","created":"2023-11-20","cited_by_count":377},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2111.14973","title":"MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction","created":"2021-11-29","cited_by_count":246},{"id":"2504.02792","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","created":"2025-04-03","cited_by_count":240},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2401.11605","title":"Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers","created":"2024-01-21","cited_by_count":118},{"id":"2410.06205","title":"Round and Round We Go! What makes Rotary Positional Encodings useful?","created":"2024-10-08","cited_by_count":115},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104},{"id":"2504.08388","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","created":"2025-04-11","cited_by_count":97},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66},{"id":"1511.07404","title":"Learning Visual Predictive Models of Physics for Playing Billiards","created":"2015-11-23","cited_by_count":58},{"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":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49},{"id":"1905.11169","title":"Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video","created":"2019-05-27","cited_by_count":45},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45},{"id":"2505.18151","title":"WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions","created":"2025-05-23","cited_by_count":45},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42},{"id":"2505.09723","title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","created":"2025-05-14","cited_by_count":42},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38},{"id":"2504.05579","title":"TAPNext: Tracking Any Point (TAP) as Next Token Prediction","created":"2025-04-08","cited_by_count":37},{"id":"1505.00295","title":"Dense Optical Flow Prediction from a Static Image","created":"2015-05-02","cited_by_count":36},{"id":"2601.09499","title":"V-DPM: 4D Video Reconstruction with Dynamic Point Maps","created":"2026-01-14","cited_by_count":34},{"id":"2409.08857","title":"InstantDrag: Improving Interactivity in Drag-based Image Editing","created":"2024-09-13","cited_by_count":31},{"id":"2408.04631","title":"Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics","created":"2024-08-08","cited_by_count":28},{"id":"1511.04048","title":"Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images","created":"2015-11-12","cited_by_count":26},{"id":"1712.04109","title":"Im2Flow: Motion Hallucination from Static Images for Action Recognition","created":"2017-12-12","cited_by_count":24},{"id":"1603.05600","title":"\"What happens if...\" Learning to Predict the Effect of Forces in Images","created":"2016-03-17","cited_by_count":23},{"id":"2506.01380","title":"Playing with Transformer at 30+ FPS via Next-Frame Diffusion","created":"2025-06-02","cited_by_count":20},{"id":"2311.11325","title":"MoVideo: Motion-Aware Video Generation with Diffusion Models","created":"2023-11-19","cited_by_count":15},{"id":"2504.01019","title":"MixerMDM: Learnable Composition of Human Motion Diffusion Models","created":"2025-04-01","cited_by_count":13},{"id":"2312.06721","title":"Understanding Physical Dynamics with Counterfactual World Modeling","created":"2023-12-11","cited_by_count":11},{"id":"2509.21592","title":"What Happens Next? Anticipating Future Motion by Generating Point Trajectories","created":"2025-09-25","cited_by_count":10},{"id":"1803.06951","title":"Deja Vu: Motion Prediction in Static Images","created":"2018-03-19","cited_by_count":7},{"id":"2503.12348","title":"ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation","created":"2025-03-16","cited_by_count":2},{"id":"2510.12777","title":"What If : Understanding Motion Through Sparse Interactions","created":"2025-10-14","cited_by_count":2},{"id":"2410.03860","title":"MDMP: Multi-modal Diffusion for supervised Motion Predictions with uncertainty","created":"2024-10-04","cited_by_count":1}],"next_cursor":null}