{"list":"other","total":80,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"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":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2002.09405","title":"Learning to Simulate Complex Physics with Graph Networks","created":"2020-02-21","cited_by_count":880},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"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":"2311.12198","title":"PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics","created":"2023-11-20","cited_by_count":377},{"id":"2409.06765","title":"gsplat: An Open-Source Library for Gaussian Splatting","created":"2024-09-10","cited_by_count":285},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"id":"2403.09434","title":"Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians","created":"2024-03-14","cited_by_count":97},{"id":"2503.17973","title":"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos","created":"2025-03-23","cited_by_count":87},{"id":"2510.22200","title":"LongCat-Video Technical Report","created":"2025-10-25","cited_by_count":85},{"id":"2211.09423","title":"DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation","created":"2022-11-17","cited_by_count":84},{"id":"2303.10880","title":"Rotating without Seeing: Towards In-hand Dexterity through Touch","created":"2023-03-20","cited_by_count":84},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76},{"id":"2106.05306","title":"DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact","created":"2021-06-09","cited_by_count":65},{"id":"1809.11169","title":"Propagation Networks for Model-Based Control Under Partial Observation","created":"2018-09-28","cited_by_count":64},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54},{"id":"2407.07889","title":"AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation","created":"2024-07-10","cited_by_count":54},{"id":"2512.10675","title":"Evaluating Gemini Robotics Policies in a Veo World Simulator","created":"2025-12-11","cited_by_count":51},{"id":"2411.06449","title":"Improved Video VAE for Latent Video Diffusion Model","created":"2024-11-10","cited_by_count":48},{"id":"2410.18912","title":"Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling","created":"2024-10-24","cited_by_count":43},{"id":"2312.00583","title":"DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation","created":"2023-11-30","cited_by_count":42},{"id":"2303.02346","title":"FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation","created":"2023-03-04","cited_by_count":40},{"id":"2510.08568","title":"NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos","created":"2025-10-09","cited_by_count":40},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38},{"id":"2603.12231","title":"Temporal Straightening for Latent Planning","created":"2026-03-12","cited_by_count":38},{"id":"2511.09057","title":"PAN: A World Model for General, Actionable, and Long-Horizon World Simulation","created":"2025-11-12","cited_by_count":36},{"id":"2603.08546","title":"Interactive World Simulator for Robot Policy Training and Evaluation","created":"2026-03-09","cited_by_count":31},{"id":"2507.15062","title":"Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper","created":"2025-07-20","cited_by_count":29},{"id":"2407.05560","title":"A Review of Differentiable Simulators","created":"2024-07-08","cited_by_count":28},{"id":"2312.02137","title":"MANUS: Markerless Grasp Capture using Articulated 3D Gaussians","created":"2023-12-04","cited_by_count":26},{"id":"2506.23126","title":"ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation","created":"2025-06-29","cited_by_count":26},{"id":"2506.15680","title":"Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos","created":"2025-06-18","cited_by_count":25},{"id":"2308.09987","title":"ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environment","created":"2023-08-19","cited_by_count":23},{"id":"2601.23286","title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","created":"2026-01-30","cited_by_count":23},{"id":"2509.21245","title":"Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets","created":"2025-09-25","cited_by_count":22},{"id":"2203.15004","title":"Offline-Online Learning of Deformation Model for Cable Manipulation with Graph Neural Networks","created":"2022-03-28","cited_by_count":17},{"id":"2310.09543","title":"Benchmarking the Sim-to-Real Gap in Cloth Manipulation","created":"2023-10-14","cited_by_count":17},{"id":"2512.16906","title":"VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization","created":"2025-12-18","cited_by_count":16},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14},{"id":"2301.07652","title":"HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects","created":"2023-01-18","cited_by_count":12},{"id":"2406.05931","title":"Differentiable Discrete Elastic Rods for Real-Time Modeling of Deformable Linear Objects","created":"2024-06-09","cited_by_count":10},{"id":"2312.06686","title":"Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset","created":"2023-12-09","cited_by_count":9},{"id":"2601.17251","title":"EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects","created":"2026-01-24","cited_by_count":9},{"id":"2506.03103","title":"DyTact: Capturing Dynamic Contacts in Hand-Object Manipulation","created":"2025-06-03","cited_by_count":8},{"id":"2602.20119","title":"NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning","created":"2026-02-23","cited_by_count":8},{"id":"2111.01527","title":"Household Cloth Object Set: Fostering Benchmarking in Deformable Object Manipulation","created":"2021-11-02","cited_by_count":7},{"id":"2310.09899","title":"Generalizable whole-body global manipulation of deformable linear objects by dual-arm robot in 3-D constrained environments","created":"2023-10-15","cited_by_count":6},{"id":"2408.08312","title":"HyperTaxel: Hyper-Resolution for Taxel-Based Tactile Signals Through Contrastive Learning","created":"2024-08-15","cited_by_count":6},{"id":"2406.10167","title":"4DRecons: 4D Neural Implicit Deformable Objects Reconstruction from a single RGB-D Camera with Geometrical and Topological Regularizations","created":"2024-06-14","cited_by_count":5},{"id":"2502.17434","title":"V-HOP: Visuo-Haptic 6D Object Pose Tracking","created":"2025-02-24","cited_by_count":5},{"id":"2410.07688","title":"PokeFlex: A Real-World Dataset of Volumetric Deformable Objects for Robotics","created":"2024-10-10","cited_by_count":4},{"id":"2504.13179","title":"ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation","created":"2025-04-17","cited_by_count":3}],"next_cursor":null}