{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"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":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2506.08052","title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","created":"2025-06-09","cited_by_count":198},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2506.15442","title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","created":"2025-06-18","cited_by_count":165},{"id":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"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":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101},{"id":"1811.12328","title":"InverseRenderNet: Learning single image inverse rendering","created":"2018-11-29","cited_by_count":100},{"id":"2203.07724","title":"CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving","created":"2022-03-15","cited_by_count":100},{"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":"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":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56},{"id":"2411.11706","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","created":"2024-11-18","cited_by_count":54},{"id":"2405.02363","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","created":"2024-05-03","cited_by_count":44},{"id":"2406.09386","title":"SimGen: Simulator-conditioned Driving Scene Generation","created":"2024-06-13","cited_by_count":34},{"id":"2403.19438","title":"SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control","created":"2024-03-28","cited_by_count":32},{"id":"2409.01595","title":"DiVE: DiT-based Video Generation with Enhanced Control","created":"2024-09-03","cited_by_count":31},{"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":"2407.11682","title":"MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation","created":"2024-07-16","cited_by_count":26},{"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":"2506.07826","title":"R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation","created":"2025-06-09","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":"2408.09481","title":"PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2024-08-18","cited_by_count":13},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13},{"id":"2509.23402","title":"WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving","created":"2025-09-27","cited_by_count":13},{"id":"2406.10722","title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","created":"2024-06-15","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":"2510.10660","title":"Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping","created":"2025-10-12","cited_by_count":7},{"id":"2508.20471","title":"Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation","created":"2025-08-28","cited_by_count":6},{"id":"2501.17261","title":"NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations","created":"2024-08-22","cited_by_count":5},{"id":"2309.15411","title":"3D Multiple Object Tracking on Autonomous Driving: A Literature Review","created":"2023-09-27","cited_by_count":4},{"id":"2501.03173","title":"MObI: Multimodal Object Inpainting Using Diffusion Models","created":"2025-01-06","cited_by_count":4},{"id":"2504.16740","title":"Gaussian Splatting is an Effective Data Generator for 3D Object Detection","created":"2025-04-23","cited_by_count":2}],"next_cursor":null}