{"list":"other","total":53,"rows":[{"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":"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2403.16999","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","created":"2024-03-25","cited_by_count":280},{"id":"2207.14024","title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","created":"2022-07-28","cited_by_count":212},{"id":"2507.21802","title":"MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE","created":"2025-07-29","cited_by_count":178},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173},{"id":"2503.15558","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","created":"2025-03-18","cited_by_count":164},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2402.05935","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","created":"2024-02-08","cited_by_count":131},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2403.04133","title":"Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving","created":"2024-03-07","cited_by_count":104},{"id":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94},{"id":"2305.10507","title":"ReasonNet: End-to-End Driving with Temporal and Global Reasoning","created":"2023-05-17","cited_by_count":93},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"2404.13046","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","created":"2024-04-19","cited_by_count":83},{"id":"2408.10845","title":"CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving","created":"2024-08-19","cited_by_count":77},{"id":"2407.01094","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","created":"2024-07-01","cited_by_count":67},{"id":"2505.09694","title":"EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models","created":"2025-05-14","cited_by_count":50},{"id":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45},{"id":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36},{"id":"2406.12095","title":"DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features","created":"2024-06-17","cited_by_count":33},{"id":"2401.01651","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","created":"2024-01-03","cited_by_count":27},{"id":"2412.09618","title":"EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM","created":"2024-12-12","cited_by_count":25},{"id":"2010.14712","title":"Socially-Compatible Behavior Design of Autonomous Vehicles with Verification on Real Human Data","created":"2020-10-28","cited_by_count":18},{"id":"2311.11013","title":"Implicit Event-RGBD Neural SLAM","created":"2023-11-18","cited_by_count":16},{"id":"2410.08669","title":"SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction","created":"2024-10-11","cited_by_count":7},{"id":"2411.13609","title":"What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality","created":"2024-11-20","cited_by_count":6},{"id":"2412.11279","title":"VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping","created":"2024-12-15","cited_by_count":6},{"id":"2503.08120","title":"UniF$^2$ace: A Unified Fine-grained Face Understanding and Generation Model","created":"2025-03-11","cited_by_count":5},{"id":"2503.08122","title":"Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments","created":"2025-03-11","cited_by_count":5},{"id":"2503.22179","title":"High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning","created":"2025-03-28","cited_by_count":5}],"next_cursor":null}