{"list":"other","total":58,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217},{"id":"2503.19755","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","created":"2025-03-25","cited_by_count":178},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151},{"id":"2311.18561","title":"Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering","created":"2023-11-30","cited_by_count":143},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2312.09866","title":"PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment","created":"2023-12-15","cited_by_count":63},{"id":"2501.00602","title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes","created":"2024-12-31","cited_by_count":55},{"id":"2409.12753","title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","created":"2024-09-19","cited_by_count":53},{"id":"2410.18079","title":"FreeVS: Generative View Synthesis on Free Driving Trajectory","created":"2024-10-23","cited_by_count":53},{"id":"2410.08114","title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","created":"2024-10-10","cited_by_count":43},{"id":"2303.10209","title":"CAPE: Camera View Position Embedding for Multi-View 3D Object Detection","created":"2023-03-17","cited_by_count":40},{"id":"2503.15208","title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","created":"2025-03-19","cited_by_count":40},{"id":"2411.11252","title":"DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation","created":"2024-11-18","cited_by_count":34},{"id":"2511.22018","title":"MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis","created":"2025-11-27","cited_by_count":32},{"id":"2403.20034","title":"NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising","created":"2024-03-29","cited_by_count":30},{"id":"2411.16805","title":"Human Motion Instruction Tuning","created":"2024-11-25","cited_by_count":29},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29},{"id":"2503.13587","title":"UniFuture: A 4D Driving World Model for Future Generation and Perception","created":"2025-03-17","cited_by_count":22},{"id":"2511.22033","title":"Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosis","created":"2025-11-27","cited_by_count":22},{"id":"2505.20897","title":"Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation","created":"2025-05-27","cited_by_count":17},{"id":"2505.18992","title":"VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes","created":"2025-05-25","cited_by_count":13},{"id":"2507.00886","title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","created":"2025-07-01","cited_by_count":12},{"id":"2506.18678","title":"MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation","created":"2025-06-23","cited_by_count":11},{"id":"2505.08725","title":"Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving","created":"2025-05-13","cited_by_count":10},{"id":"2507.22052","title":"Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos","created":"2025-07-29","cited_by_count":10},{"id":"2509.24156","title":"Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models","created":"2025-09-29","cited_by_count":10},{"id":"2412.00623","title":"A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision","created":"2024-12-01","cited_by_count":9},{"id":"2509.07500","title":"OmniMap: A General Mapping Framework Integrating Optics, Geometry, and Semantics","created":"2025-09-09","cited_by_count":9},{"id":"2412.04903","title":"EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation","created":"2024-12-06","cited_by_count":8},{"id":"2406.08009","title":"OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding","created":"2024-06-12","cited_by_count":6},{"id":"2507.11001","title":"Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation","created":"2025-07-15","cited_by_count":6},{"id":"2507.19474","title":"DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations","created":"2025-07-25","cited_by_count":6},{"id":"2512.19554","title":"CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning","created":"2025-12-22","cited_by_count":4},{"id":"2505.09406","title":"FreeDriveRF: Monocular RGB Dynamic NeRF without Poses for Autonomous Driving via Point-Level Dynamic-Static Decoupling","created":"2025-05-14","cited_by_count":3},{"id":"2504.08361","title":"SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis","created":"2025-04-11","cited_by_count":2},{"id":"2510.23574","title":"More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models","created":"2025-10-27","cited_by_count":2}],"next_cursor":null}