{"list":"other","total":81,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"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":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"1910.05449","title":"MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction","created":"2019-10-12","cited_by_count":420},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"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":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2402.13243","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","created":"2024-02-20","cited_by_count":289},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"1911.10298","title":"CoverNet: Multimodal Behavior Prediction using Trajectory Sets","created":"2019-11-23","cited_by_count":259},{"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":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245},{"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":"2405.19620","title":"SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation","created":"2024-05-30","cited_by_count":241},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2312.09245","title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","created":"2023-12-14","cited_by_count":233},{"id":"2012.12395","title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","created":"2020-12-22","cited_by_count":228},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2103.11624","title":"Multimodal Motion Prediction with Stacked Transformers","created":"2021-03-22","cited_by_count":208},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194},{"id":"2305.10430","title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","created":"2023-05-17","cited_by_count":191},{"id":"2305.06242","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","created":"2023-05-10","cited_by_count":169},{"id":"2106.08417","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","created":"2021-06-15","cited_by_count":165},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"id":"2311.15260","title":"NeuRAD: Neural Rendering for Autonomous Driving","created":"2023-11-26","cited_by_count":150},{"id":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","cited_by_count":144},{"id":"2308.00398","title":"DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving","created":"2023-08-01","cited_by_count":144},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"id":"2101.06547","title":"LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving","created":"2021-01-16","cited_by_count":96},{"id":"2312.14074","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding","created":"2023-12-21","cited_by_count":95},{"id":"2305.10507","title":"ReasonNet: End-to-End Driving with Temporal and Global Reasoning","created":"2023-05-17","cited_by_count":93},{"id":"2308.01006","title":"FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving","created":"2023-08-02","cited_by_count":67},{"id":"2404.07762","title":"NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving","created":"2024-04-11","cited_by_count":62},{"id":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60},{"id":"2103.13575","title":"MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation","created":"2021-03-25","cited_by_count":54},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49},{"id":"1801.10068","title":"Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization","created":"2018-01-30","cited_by_count":40},{"id":"1807.01726","title":"LaneNet: Real-Time Lane Detection Networks for Autonomous Driving","created":"2018-07-04","cited_by_count":39},{"id":"2403.15992","title":"BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval","created":"2024-03-24","cited_by_count":30},{"id":"2212.02181","title":"Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction","created":"2022-12-05","cited_by_count":28},{"id":"2407.19323","title":"MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo","created":"2024-07-27","cited_by_count":17},{"id":"2412.12704","title":"MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert","created":"2024-12-17","cited_by_count":17},{"id":"2412.11578","title":"DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo","created":"2024-12-16","cited_by_count":12},{"id":"2206.10118","title":"HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction","created":"2022-06-21","cited_by_count":11},{"id":"2411.12980","title":"LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement","created":"2024-11-20","cited_by_count":9},{"id":"2409.00301","title":"ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models","created":"2024-08-30","cited_by_count":8},{"id":"2501.02149","title":"Attribute-Based Robotic Grasping with Data-Efficient Adaptation","created":"2025-01-04","cited_by_count":8},{"id":"2405.16847","title":"TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation","created":"2024-05-27","cited_by_count":7},{"id":"2508.17703","title":"EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning","created":"2025-08-25","cited_by_count":6},{"id":"2506.13215","title":"DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo","created":"2025-06-16","cited_by_count":4},{"id":"2412.16948","title":"DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network","created":"2024-12-22","cited_by_count":3},{"id":"2501.05265","title":"Patch-GAN Transfer Learning with Reconstructive Models for Cloud Removal","created":"2025-01-09","cited_by_count":2},{"id":"2501.17384","title":"A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning","created":"2025-01-29","cited_by_count":1}],"next_cursor":null}