{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2312.00109","title":"Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering","created":"2023-11-30","cited_by_count":695},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2310.01415","title":"GPT-Driver: Learning to Drive with GPT","created":"2023-10-02","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":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2402.14650","title":"GaussianPro: 3D Gaussian Splatting with Progressive Propagation","created":"2024-02-22","cited_by_count":200},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2504.04348","title":"OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning","created":"2025-04-06","cited_by_count":143},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129},{"id":"2301.04634","title":"Street-View Image Generation from a Bird's-Eye View Layout","created":"2023-01-11","cited_by_count":102},{"id":"2308.01661","title":"BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout","created":"2023-08-03","cited_by_count":102},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98},{"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":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2405.14475","title":"MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes","created":"2024-05-23","cited_by_count":71},{"id":"2412.03934","title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models","created":"2024-12-05","cited_by_count":56},{"id":"2404.13679","title":"GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal","created":"2024-04-21","cited_by_count":39},{"id":"2407.13759","title":"Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion","created":"2024-07-18","cited_by_count":39},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38},{"id":"2506.05558","title":"On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images","created":"2025-06-05","cited_by_count":36},{"id":"2403.19438","title":"SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control","created":"2024-03-28","cited_by_count":32},{"id":"2402.02112","title":"S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation","created":"2024-02-03","cited_by_count":28},{"id":"2412.19458","title":"DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes","created":"2024-12-27","cited_by_count":17},{"id":"2408.08524","title":"GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors","created":"2024-08-16","cited_by_count":14},{"id":"2504.05445","title":"Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly","created":"2025-04-07","cited_by_count":11},{"id":"2509.17985","title":"VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models","created":"2025-09-22","cited_by_count":8},{"id":"2002.00328","title":"Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction","created":"2020-02-02","cited_by_count":7},{"id":"2507.01735","title":"ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving","created":"2025-07-02","cited_by_count":5},{"id":"2509.19937","title":"GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes","created":"2025-09-24","cited_by_count":5},{"id":"2505.01486","title":"Aerial Path Online Planning for Urban Scene Updation","created":"2025-05-02","cited_by_count":4},{"id":"2312.09609","title":"Semantic-Aware Transformation-Invariant RoI Align","created":"2023-12-15","cited_by_count":1}],"next_cursor":null}