{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"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":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2211.10439","title":"BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision","created":"2022-11-18","cited_by_count":302},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2403.01823","title":"RT-H: Action Hierarchies Using Language","created":"2024-03-04","cited_by_count":210},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191},{"id":"2210.02443","title":"Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection","created":"2022-10-05","cited_by_count":178},{"id":"2004.12636","title":"3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection","created":"2020-04-27","cited_by_count":176},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2312.00438","title":"Dolphins: Multimodal Language Model for Driving","created":"2023-12-01","cited_by_count":124},{"id":"2311.13549","title":"ADriver-I: A General World Model for Autonomous Driving","created":"2023-11-22","cited_by_count":104},{"id":"2308.02236","title":"FB-BEV: BEV Representation from Forward-Backward View Transformations","created":"2023-08-04","cited_by_count":98},{"id":"2204.13683","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","created":"2022-04-28","cited_by_count":96},{"id":"2205.02222","title":"COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles","created":"2022-05-04","cited_by_count":95},{"id":"2209.10248","title":"BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo","created":"2022-09-21","cited_by_count":90},{"id":"2401.00988","title":"Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models","created":"2024-01-02","cited_by_count":76},{"id":"2201.06493","title":"AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection","created":"2022-01-17","cited_by_count":70},{"id":"2403.16996","title":"DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving","created":"2024-03-25","cited_by_count":67},{"id":"2403.04593","title":"Embodied Understanding of Driving Scenarios","created":"2024-03-07","cited_by_count":63},{"id":"2209.03102","title":"MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection","created":"2022-09-07","cited_by_count":62},{"id":"2205.15938","title":"Voxel Field Fusion for 3D Object Detection","created":"2022-05-31","cited_by_count":50},{"id":"2309.15109","title":"DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation","created":"2023-09-26","cited_by_count":41},{"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":"2307.16118","title":"MTD-GPT: A Multi-Task Decision-Making GPT Model for Autonomous Driving at Unsignalized Intersections","created":"2023-07-30","cited_by_count":38},{"id":"2312.01696","title":"BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection","created":"2023-12-04","cited_by_count":35},{"id":"2403.18344","title":"LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Models","created":"2024-03-27","cited_by_count":35},{"id":"2307.11477","title":"SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection","created":"2023-07-21","cited_by_count":30},{"id":"2211.10593","title":"MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception","created":"2022-11-19","cited_by_count":29},{"id":"2301.04467","title":"FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection","created":"2023-01-10","cited_by_count":21},{"id":"2403.19622","title":"RH20T-P: A Primitive-Level Robotic Dataset Towards Composable Generalization Agents","created":"2024-03-28","cited_by_count":20},{"id":"2403.11368","title":"Driving Style Alignment for LLM-powered Driver Agent","created":"2024-03-17","cited_by_count":15},{"id":"2006.04843","title":"Modeling Long-horizon Tasks as Sequential Interaction Landscapes","created":"2020-06-08","cited_by_count":14},{"id":"2309.07084","title":"SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection","created":"2023-09-13","cited_by_count":14},{"id":"2403.20116","title":"LeGo-Drive: Language-enhanced Goal-oriented Closed-Loop End-to-End Autonomous Driving","created":"2024-03-29","cited_by_count":12},{"id":"2403.18965","title":"LORD: Large Models based Opposite Reward Design for Autonomous Driving","created":"2024-03-27","cited_by_count":6},{"id":"2402.04883","title":"Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration","created":"2024-02-07","cited_by_count":3}],"next_cursor":null}