{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"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":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191},{"id":"2408.16760","title":"OmniRe: Omni Urban Scene Reconstruction","created":"2024-08-29","cited_by_count":161},{"id":"2503.01774","title":"Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models","created":"2025-03-03","cited_by_count":161},{"id":"2304.01893","title":"Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion","created":"2023-04-04","cited_by_count":138},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134},{"id":"2503.05638","title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","created":"2025-03-07","cited_by_count":125},{"id":"2402.05746","title":"Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents","created":"2024-02-08","cited_by_count":91},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78},{"id":"2510.26125","title":"WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios","created":"2025-10-30","cited_by_count":62},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48},{"id":"2304.11846","title":"Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions","created":"2023-04-24","cited_by_count":43},{"id":"2204.12684","title":"Density-preserving Deep Point Cloud Compression","created":"2022-04-27","cited_by_count":39},{"id":"2503.10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","created":"2025-03-13","cited_by_count":35},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27},{"id":"2404.19722","title":"PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios","created":"2024-04-30","cited_by_count":24},{"id":"2412.07320","title":"CoMA: Compositional Human Motion Generation with Multi-modal Agents","created":"2024-12-10","cited_by_count":19},{"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":"2408.10453","title":"Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation","created":"2024-08-19","cited_by_count":16},{"id":"2503.13684","title":"FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models","created":"2025-03-17","cited_by_count":16},{"id":"2405.00900","title":"LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes","created":"2024-05-01","cited_by_count":14},{"id":"2504.11521","title":"LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation","created":"2025-04-15","cited_by_count":11},{"id":"2506.19488","title":"SceneCrafter: Controllable Multi-View Driving Scene Editing","created":"2025-06-24","cited_by_count":9},{"id":"2403.13199","title":"DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images","created":"2024-03-19","cited_by_count":4},{"id":"2508.20965","title":"DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes","created":"2025-08-28","cited_by_count":4},{"id":"2412.08685","title":"ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenes","created":"2024-12-11","cited_by_count":3},{"id":"2510.02469","title":"SIMSplat: Language-Aligned 4D Gaussian Splatting for Driving Scenario Generation","created":"2025-10-02","cited_by_count":1}],"next_cursor":null}