{"list":"other","total":101,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2201.11793","title":"Denoising Diffusion Restoration Models","created":"2022-01-27","cited_by_count":963},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"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":"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":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"2405.19620","title":"SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation","created":"2024-05-30","cited_by_count":241},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191},{"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":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"1904.05050","title":"Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning","created":"2019-04-10","cited_by_count":157},{"id":"2008.03156","title":"Better Fine-Tuning by Reducing Representational Collapse","created":"2020-08-06","cited_by_count":157},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132},{"id":"1911.12676","title":"xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation","created":"2019-11-28","cited_by_count":129},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"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":"2408.00415","title":"DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving","created":"2024-08-01","cited_by_count":98},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96},{"id":"2312.02934","title":"WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation","created":"2023-12-05","cited_by_count":93},{"id":"2402.05746","title":"Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents","created":"2024-02-08","cited_by_count":91},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89},{"id":"2001.10117","title":"Canadian Adverse Driving Conditions Dataset","created":"2020-01-27","cited_by_count":87},{"id":"2506.09042","title":"Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models","created":"2025-06-10","cited_by_count":84},{"id":"2405.14881","title":"DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models","created":"2024-04-05","cited_by_count":78},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75},{"id":"2208.00223","title":"PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds","created":"2022-07-30","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":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61},{"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":"2501.14729","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","created":"2025-01-24","cited_by_count":56},{"id":"2205.05509","title":"READ: Large-Scale Neural Scene Rendering for Autonomous Driving","created":"2022-05-11","cited_by_count":51},{"id":"2504.13175","title":"Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation","created":"2025-04-17","cited_by_count":48},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43},{"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":"2306.06048","title":"How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?","created":"2023-06-09","cited_by_count":38},{"id":"2506.11526","title":"Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis","created":"2025-06-13","cited_by_count":38},{"id":"2211.13226","title":"ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field","created":"2022-11-23","cited_by_count":37},{"id":"2404.04804","title":"Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving","created":"2024-04-07","cited_by_count":35},{"id":"2406.09386","title":"SimGen: Simulator-conditioned Driving Scene Generation","created":"2024-06-13","cited_by_count":34},{"id":"2411.11252","title":"DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation","created":"2024-11-18","cited_by_count":34},{"id":"2203.04600","title":"Domain Generalization using Pretrained Models without Fine-tuning","created":"2022-03-09","cited_by_count":29},{"id":"2403.11530","title":"Continual Forgetting for Pre-trained Vision Models","created":"2024-03-18","cited_by_count":29},{"id":"2212.08914","title":"Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark","created":"2022-12-17","cited_by_count":26},{"id":"2409.05463","title":"DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation","created":"2024-09-09","cited_by_count":22},{"id":"2506.07497","title":"Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency","created":"2025-06-09","cited_by_count":22},{"id":"2103.05422","title":"Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks","created":"2021-03-09","cited_by_count":18},{"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":"2303.14378","title":"Instant Domain Augmentation for LiDAR Semantic Segmentation","created":"2023-03-25","cited_by_count":16},{"id":"2204.00644","title":"SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks","created":"2022-04-01","cited_by_count":15},{"id":"2510.19195","title":"Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks","created":"2025-10-22","cited_by_count":14},{"id":"2303.10340","title":"3D Data Augmentation for Driving Scenes on Camera","created":"2023-03-18","cited_by_count":12},{"id":"2410.15674","title":"TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight","created":"2024-10-21","cited_by_count":12},{"id":"2503.18108","title":"Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving","created":"2025-03-23","cited_by_count":12},{"id":"2503.22231","title":"CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving","created":"2025-03-28","cited_by_count":12},{"id":"2412.03520","title":"Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention","created":"2024-12-04","cited_by_count":11},{"id":"2407.10703","title":"Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation","created":"2024-07-15","cited_by_count":9},{"id":"2506.19488","title":"SceneCrafter: Controllable Multi-View Driving Scene Editing","created":"2025-06-24","cited_by_count":9},{"id":"2506.10145","title":"RoCA: Robust Cross-Domain End-to-End Autonomous Driving","created":"2025-06-11","cited_by_count":8},{"id":"2602.03242","title":"InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation","created":"2026-02-03","cited_by_count":8},{"id":"2407.19468","title":"MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability","created":"2024-07-28","cited_by_count":7},{"id":"2506.13138","title":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation","created":"2025-06-16","cited_by_count":5},{"id":"2509.16500","title":"RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation","created":"2025-09-20","cited_by_count":5},{"id":"2411.19390","title":"DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models","created":"2024-11-28","cited_by_count":4},{"id":"2205.00376","title":"Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving","created":"2022-05-01","cited_by_count":3},{"id":"2408.06071","title":"A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lighting","created":"2024-08-12","cited_by_count":3},{"id":"2504.18448","title":"NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and Collaboration","created":"2025-04-25","cited_by_count":3},{"id":"2510.02296","title":"Continual Personalization for Diffusion Models","created":"2025-10-02","cited_by_count":3},{"id":"2401.03771","title":"NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation","created":"2024-01-08","cited_by_count":2},{"id":"2411.00425","title":"Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editing","created":"2024-11-01","cited_by_count":2}],"next_cursor":"100"}