{"list":"other","total":60,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2310.05922","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","created":"2023-10-09","cited_by_count":167},{"id":"2204.13132","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","created":"2022-04-27","cited_by_count":164},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129},{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106},{"id":"2309.16496","title":"CCEdit: Creative and Controllable Video Editing via Diffusion Models","created":"2023-09-28","cited_by_count":82},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2009.03683","title":"Rain rendering for evaluating and improving robustness to bad weather","created":"2020-09-06","cited_by_count":57},{"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":"2405.05258","title":"Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving","created":"2024-05-08","cited_by_count":54},{"id":"2310.15171","title":"RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions","created":"2023-10-23","cited_by_count":49},{"id":"2305.13840","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","created":"2023-05-23","cited_by_count":48},{"id":"2405.17426","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","created":"2024-05-27","cited_by_count":41},{"id":"2502.04847","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","created":"2025-02-07","cited_by_count":39},{"id":"2211.13226","title":"ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field","created":"2022-11-23","cited_by_count":37},{"id":"2411.17592","title":"VideoDirector: Precise Video Editing via Text-to-Video Models","created":"2024-11-26","cited_by_count":36},{"id":"2401.12761","title":"MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty","created":"2024-01-23","cited_by_count":32},{"id":"2406.12214","title":"Is Your HD Map Constructor Reliable under Sensor Corruptions?","created":"2024-06-18","cited_by_count":28},{"id":"2509.17818","title":"ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment","created":"2025-09-22","cited_by_count":27},{"id":"2411.11045","title":"StableV2V: Stablizing Shape Consistency in Video-to-Video Editing","created":"2024-11-17","cited_by_count":26},{"id":"2405.08816","title":"The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition","created":"2024-05-14","cited_by_count":23},{"id":"2512.10958","title":"WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World","created":"2025-12-11","cited_by_count":23},{"id":"1910.03997","title":"Semantic Understanding of Foggy Scenes with Purely Synthetic Data","created":"2019-10-09","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":"2412.00397","title":"DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses","created":"2024-11-30","cited_by_count":17},{"id":"2110.02871","title":"ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods","created":"2021-10-06","cited_by_count":14},{"id":"2507.00861","title":"SafeMap: Robust HD Map Construction from Incomplete Observations","created":"2025-07-01","cited_by_count":14},{"id":"2503.21442","title":"RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting","created":"2025-03-27","cited_by_count":13},{"id":"2505.20471","title":"WeatherEdit: Controllable Weather Editing with 4D Gaussian Field","created":"2025-05-26","cited_by_count":12},{"id":"2512.11715","title":"EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing","created":"2025-12-12","cited_by_count":12},{"id":"2505.00704","title":"Controllable Weather Synthesis and Removal with Video Diffusion Models","created":"2025-05-01","cited_by_count":11},{"id":"2602.08277","title":"PISCO: Precise Video Instance Insertion with Sparse Control","created":"2026-02-09","cited_by_count":10},{"id":"2504.05296","title":"Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation","created":"2025-04-07","cited_by_count":7},{"id":"2505.19919","title":"Weather-Magician: Reconstruction and Rendering Framework for 4D Weather Synthesis In Real Time","created":"2025-05-26","cited_by_count":4},{"id":"2601.07833","title":"Tuning-free Visual Effect Transfer across Videos","created":"2026-01-12","cited_by_count":3},{"id":"2503.14845","title":"ClimateGS: Real-Time Climate Simulation with 3D Gaussian Style Transfer","created":"2025-03-19","cited_by_count":2},{"id":"2602.22096","title":"WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformation","created":"2026-02-25","cited_by_count":2}],"next_cursor":null}