{"list":"other","total":104,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2312.00109","title":"Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering","created":"2023-11-30","cited_by_count":695},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"id":"1803.04758","title":"Video Based Reconstruction of 3D People Models","created":"2018-03-13","cited_by_count":238},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233},{"id":"2403.17898","title":"Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians","created":"2024-03-26","cited_by_count":230},{"id":"2406.12080","title":"A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets","created":"2024-06-17","cited_by_count":216},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2402.17427","title":"VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction","created":"2024-02-27","cited_by_count":209},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2312.09228","title":"3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting","created":"2023-12-14","cited_by_count":195},{"id":"2404.01133","title":"CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians","created":"2024-04-01","cited_by_count":192},{"id":"2312.02134","title":"GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians","created":"2023-12-04","cited_by_count":191},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"2309.16553","title":"MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond","created":"2023-09-28","cited_by_count":185},{"id":"2408.16760","title":"OmniRe: Omni Urban Scene Reconstruction","created":"2024-08-29","cited_by_count":161},{"id":"2412.06224","title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","created":"2024-12-09","cited_by_count":156},{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147},{"id":"2406.02058","title":"OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding","created":"2024-06-04","cited_by_count":145},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2311.16099","title":"GART: Gaussian Articulated Template Models","created":"2023-11-27","cited_by_count":121},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","cited_by_count":103},{"id":"2312.11994","title":"Optimizing Diffusion Noise Can Serve As Universal Motion Priors","created":"2023-12-19","cited_by_count":98},{"id":"2012.03912","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","created":"2020-12-07","cited_by_count":95},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"2109.01137","title":"The Power of Points for Modeling Humans in Clothing","created":"2021-09-02","cited_by_count":90},{"id":"2407.21686","title":"Expressive Whole-Body 3D Gaussian Avatar","created":"2024-07-31","cited_by_count":89},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2303.04805","title":"X-Avatar: Expressive Human Avatars","created":"2023-03-08","cited_by_count":66},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61},{"id":"2112.09251","title":"The Wanderings of Odysseus in 3D Scenes","created":"2021-12-16","cited_by_count":59},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55},{"id":"2503.18052","title":"SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining","created":"2025-03-23","cited_by_count":52},{"id":"2207.06955","title":"Learning Implicit Templates for Point-Based Clothed Human Modeling","created":"2022-07-14","cited_by_count":50},{"id":"2411.00771","title":"CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes","created":"2024-11-01","cited_by_count":50},{"id":"2310.00982","title":"ViPlanner: Visual Semantic Imperative Learning for Local Navigation","created":"2023-10-02","cited_by_count":46},{"id":"2411.17820","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","created":"2024-11-26","cited_by_count":41},{"id":"2304.02061","title":"Generating Continual Human Motion in Diverse 3D Scenes","created":"2023-04-04","cited_by_count":39},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37},{"id":"2411.05755","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","created":"2024-11-08","cited_by_count":37},{"id":"2412.02684","title":"AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction","created":"2024-12-03","cited_by_count":36},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35},{"id":"2406.03175","title":"Dynamic 3D Gaussian Fields for Urban Areas","created":"2024-06-05","cited_by_count":35},{"id":"2403.13307","title":"LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment","created":"2024-03-20","cited_by_count":33},{"id":"2412.01745","title":"Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes","created":"2024-12-02","cited_by_count":30},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30},{"id":"2412.09043","title":"DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving","created":"2024-12-12","cited_by_count":29},{"id":"2404.00168","title":"Multi-Level Neural Scene Graphs for Dynamic Urban Environments","created":"2024-03-29","cited_by_count":27},{"id":"2301.05223","title":"NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants","created":"2023-01-12","cited_by_count":23},{"id":"2304.03167","title":"CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition","created":"2023-04-06","cited_by_count":21},{"id":"2405.19283","title":"Programmable Motion Generation for Open-Set Motion Control Tasks","created":"2024-05-29","cited_by_count":20},{"id":"2408.15242","title":"Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty","created":"2024-08-27","cited_by_count":20},{"id":"2009.04300","title":"SEAN: Social Environment for Autonomous Navigation","created":"2020-09-09","cited_by_count":18},{"id":"2409.17280","title":"Disco4D: Disentangled 4D Human Generation and Animation from a Single Image","created":"2024-09-25","cited_by_count":17},{"id":"2510.21307","title":"Towards Physically Executable 3D Gaussian for Embodied Navigation","created":"2025-10-24","cited_by_count":17},{"id":"2506.08710","title":"SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting","created":"2025-06-10","cited_by_count":15},{"id":"2412.15664","title":"SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control","created":"2024-12-20","cited_by_count":13},{"id":"2508.09973","title":"PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image","created":"2025-08-13","cited_by_count":13},{"id":"2503.14198","title":"RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images","created":"2025-03-18","cited_by_count":12},{"id":"2411.18624","title":"GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data","created":"2024-11-27","cited_by_count":6},{"id":"2410.07500","title":"Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels","created":"2024-10-10","cited_by_count":4}],"next_cursor":"100"}