{"list":"other","total":94,"rows":[{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2206.00665","title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","created":"2022-06-01","cited_by_count":470},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2410.06158","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","created":"2024-10-08","cited_by_count":296},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2310.01957","title":"Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","created":"2023-10-03","cited_by_count":232},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2306.14896","title":"RVT: Robotic View Transformer for 3D Object Manipulation","created":"2023-06-26","cited_by_count":225},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2503.01774","title":"Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models","created":"2025-03-03","cited_by_count":161},{"id":"2405.17429","title":"GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction","created":"2024-05-27","cited_by_count":157},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145},{"id":"2410.24185","title":"DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning","created":"2024-10-31","cited_by_count":116},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","cited_by_count":104},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99},{"id":"2412.07760","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","created":"2024-12-10","cited_by_count":93},{"id":"2411.13807","title":"MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control","created":"2024-11-21","cited_by_count":92},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"2409.03272","title":"OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving","created":"2024-09-05","cited_by_count":83},{"id":"2307.03659","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","created":"2023-07-07","cited_by_count":82},{"id":"2405.20337","title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","created":"2024-05-30","cited_by_count":78},{"id":"2212.05711","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","created":"2022-12-12","cited_by_count":71},{"id":"2405.14475","title":"MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes","created":"2024-05-23","cited_by_count":71},{"id":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63},{"id":"2501.18590","title":"DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models","created":"2025-01-30","cited_by_count":57},{"id":"2504.18904","title":"RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning","created":"2025-04-26","cited_by_count":54},{"id":"2401.09413","title":"POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images","created":"2024-01-17","cited_by_count":52},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49},{"id":"2412.13188","title":"StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models","created":"2024-12-17","cited_by_count":49},{"id":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45},{"id":"2410.12822","title":"AVID: Adapting Video Diffusion Models to World Models","created":"2024-10-01","cited_by_count":37},{"id":"2501.00601","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images","created":"2024-12-31","cited_by_count":35},{"id":"2410.11623","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","created":"2024-10-15","cited_by_count":34},{"id":"2506.01943","title":"Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control","created":"2025-06-02","cited_by_count":34},{"id":"2407.02077","title":"Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion","created":"2024-07-02","cited_by_count":32},{"id":"2411.16157","title":"MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model","created":"2024-11-25","cited_by_count":32},{"id":"2410.15461","title":"EVA: An Embodied World Model for Future Video Anticipation","created":"2024-10-20","cited_by_count":28},{"id":"2101.06005","title":"SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning","created":"2021-01-15","cited_by_count":27},{"id":"2504.09540","title":"EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler","created":"2025-04-13","cited_by_count":27},{"id":"2411.07223","title":"Grounding Video Models to Actions through Goal Conditioned Exploration","created":"2024-11-11","cited_by_count":26},{"id":"2502.04296","title":"Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression","created":"2025-02-06","cited_by_count":23},{"id":"2303.13959","title":"Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion","created":"2023-03-24","cited_by_count":22},{"id":"2406.07754","title":"HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness","created":"2024-06-11","cited_by_count":21},{"id":"2412.05280","title":"Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model","created":"2024-12-06","cited_by_count":18},{"id":"2306.12681","title":"One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception","created":"2023-06-22","cited_by_count":13},{"id":"2505.00704","title":"Controllable Weather Synthesis and Removal with Video Diffusion Models","created":"2025-05-01","cited_by_count":11},{"id":"2412.02699","title":"UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping","created":"2024-12-03","cited_by_count":10},{"id":"2303.07026","title":"Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks","created":"2023-03-13","cited_by_count":7},{"id":"2210.12682","title":"Photo-realistic Neural Domain Randomization","created":"2022-10-23","cited_by_count":5},{"id":"2307.15320","title":"Robust Visual Sim-to-Real Transfer for Robotic Manipulation","created":"2023-07-28","cited_by_count":5},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4},{"id":"2311.08393","title":"MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation","created":"2023-11-14","cited_by_count":3}],"next_cursor":null}