{"list":"other","total":55,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"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":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"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":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"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":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"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":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193},{"id":"1910.06528","title":"End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds","created":"2019-10-15","cited_by_count":171},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"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":"2209.05588","title":"CenterFormer: Center-based Transformer for 3D Object Detection","created":"2022-09-12","cited_by_count":99},{"id":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92},{"id":"2207.10035","title":"Fully Sparse 3D Object Detection","created":"2022-07-20","cited_by_count":84},{"id":"2303.03595","title":"LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion","created":"2023-03-07","cited_by_count":80},{"id":"2310.08370","title":"UniPAD: A Universal Pre-training Paradigm for Autonomous Driving","created":"2023-10-12","cited_by_count":73},{"id":"2005.03844","title":"SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving","created":"2020-05-08","cited_by_count":68},{"id":"2403.05817","title":"SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection","created":"2024-03-09","cited_by_count":52},{"id":"2310.20234","title":"HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds","created":"2023-10-31","cited_by_count":45},{"id":"2406.08691","title":"UnO: Unsupervised Occupancy Fields for Perception and Forecasting","created":"2024-06-12","cited_by_count":41},{"id":"2207.00531","title":"Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds","created":"2022-07-01","cited_by_count":39},{"id":"2310.19956","title":"The Impact of Depth on Compositional Generalization in Transformer Language Models","created":"2023-10-30","cited_by_count":38},{"id":"2407.18232","title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","created":"2024-07-25","cited_by_count":38},{"id":"2308.03755","title":"FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels","created":"2023-08-07","cited_by_count":34},{"id":"2301.02562","title":"Super Sparse 3D Object Detection","created":"2023-01-05","cited_by_count":32},{"id":"2412.14415","title":"DriveGPT: Scaling Autoregressive Behavior Models for Driving","created":"2024-12-19","cited_by_count":29},{"id":"2407.10749","title":"SEED: A Simple and Effective 3D DETR in Point Clouds","created":"2024-07-15","cited_by_count":19},{"id":"2506.08228","title":"Scaling Laws of Motion Forecasting and Planning -- Technical Report","created":"2025-06-09","cited_by_count":19},{"id":"2303.08316","title":"MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences","created":"2023-03-15","cited_by_count":15},{"id":"2306.03206","title":"MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences","created":"2023-06-05","cited_by_count":13},{"id":"2308.12779","title":"On Offline Evaluation of 3D Object Detection for Autonomous Driving","created":"2023-08-24","cited_by_count":11},{"id":"2410.23085","title":"S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving","created":"2024-10-30","cited_by_count":4},{"id":"2503.15672","title":"GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving","created":"2025-03-19","cited_by_count":4},{"id":"2411.13186","title":"VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation","created":"2024-11-20","cited_by_count":2}],"next_cursor":null}