{"list":"other","total":82,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"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":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446},{"id":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"2406.15349","title":"NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking","created":"2024-06-21","cited_by_count":354},{"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":"2411.15139","title":"DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving","created":"2024-11-22","cited_by_count":334},{"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":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2402.13243","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","created":"2024-02-20","cited_by_count":289},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2312.03031","title":"Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?","created":"2023-12-05","cited_by_count":242},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2410.23262","title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","created":"2024-10-30","cited_by_count":231},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2406.08481","title":"Enhancing End-to-End Autonomous Driving with Latent World Model","created":"2024-06-12","cited_by_count":166},{"id":"2311.10813","title":"A Language Agent for Autonomous Driving","created":"2023-11-17","cited_by_count":164},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"2210.07729","title":"Model-Based Imitation Learning for Urban Driving","created":"2022-10-14","cited_by_count":150},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150},{"id":"2307.08041","title":"Planting a SEED of Vision in Large Language Model","created":"2023-07-16","cited_by_count":140},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"2209.09002","title":"MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation","created":"2022-09-19","cited_by_count":125},{"id":"2312.00438","title":"Dolphins: Multimodal Language Model for Driving","created":"2023-12-01","cited_by_count":124},{"id":"2312.03661","title":"Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving","created":"2023-12-06","cited_by_count":123},{"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":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2312.17655","title":"Visual Point Cloud Forecasting enables Scalable Autonomous Driving","created":"2023-12-29","cited_by_count":99},{"id":"2412.18607","title":"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers","created":"2024-12-24","cited_by_count":96},{"id":"2405.04390","title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","created":"2024-05-07","cited_by_count":93},{"id":"2405.14062","title":"ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles","created":"2024-05-22","cited_by_count":93},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89},{"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":"2412.06673","title":"ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance","created":"2024-12-09","cited_by_count":64},{"id":"2403.04593","title":"Embodied Understanding of Driving Scenarios","created":"2024-03-07","cited_by_count":63},{"id":"2402.05932","title":"Driving Everywhere with Large Language Model Policy Adaptation","created":"2024-02-08","cited_by_count":53},{"id":"2408.13890","title":"Making Large Language Models Better Planners with Reasoning-Decision Alignment","created":"2024-08-25","cited_by_count":52},{"id":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2412.09627","title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","created":"2024-12-12","cited_by_count":51},{"id":"2502.18041","title":"Openfly: A comprehensive platform for aerial vision-language navigation","created":"2025-02-25","cited_by_count":46},{"id":"2405.15324","title":"Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving","created":"2024-05-24","cited_by_count":41},{"id":"2501.03747","title":"Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series","created":"2025-01-07","cited_by_count":39},{"id":"2410.18084","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes","created":"2024-10-23","cited_by_count":38},{"id":"2405.03685","title":"Language-Image Models with 3D Understanding","created":"2024-05-06","cited_by_count":31},{"id":"2411.18499","title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","created":"2024-11-27","cited_by_count":31},{"id":"2502.07309","title":"Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving","created":"2025-02-11","cited_by_count":29},{"id":"2502.11663","title":"MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction","created":"2025-02-17","cited_by_count":29},{"id":"2502.06419","title":"Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models","created":"2025-02-10","cited_by_count":28},{"id":"2501.00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","created":"2024-12-31","cited_by_count":25},{"id":"2505.06068","title":"Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation","created":"2025-05-09","cited_by_count":23},{"id":"2407.21293","title":"SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving","created":"2024-07-31","cited_by_count":16},{"id":"2410.23780","title":"Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map","created":"2024-10-31","cited_by_count":11},{"id":"2503.06260","title":"From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models","created":"2025-03-08","cited_by_count":11},{"id":"2504.12574","title":"ForgetMe: Evaluating Selective Forgetting in Generative Models","created":"2025-04-17","cited_by_count":11},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10},{"id":"2501.08001","title":"GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation","created":"2025-01-14","cited_by_count":7},{"id":"2502.10705","title":"CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning","created":"2025-02-15","cited_by_count":7},{"id":"2503.14498","title":"Tracking Meets Large Multimodal Models for Driving Scenario Understanding","created":"2025-03-18","cited_by_count":7},{"id":"2505.11175","title":"Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition","created":"2025-05-16","cited_by_count":3},{"id":"2410.08068","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","created":"2024-10-10","cited_by_count":2}],"next_cursor":null}