{"list":"other","total":53,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"2203.00680","title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","created":"2022-03-01","cited_by_count":198},{"id":"2010.01089","title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","created":"2020-10-02","cited_by_count":186},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2505.03233","title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","created":"2025-05-06","cited_by_count":123},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110},{"id":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86},{"id":"2003.12971","title":"Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds","created":"2020-03-29","cited_by_count":75},{"id":"2303.14191","title":"Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning","created":"2023-03-24","cited_by_count":56},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45},{"id":"2509.06784","title":"P3-SAM: Native 3D Part Segmentation","created":"2025-09-08","cited_by_count":43},{"id":"2305.08808","title":"GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training","created":"2023-05-15","cited_by_count":38},{"id":"2412.16490","title":"BODex: Scalable and Efficient Robotic Dexterous Grasp Synthesis Using Bilevel Optimization","created":"2024-12-21","cited_by_count":20},{"id":"2512.13689","title":"LitePT: Lighter Yet Stronger Point Transformer","created":"2025-12-15","cited_by_count":17},{"id":"2602.00807","title":"Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds","created":"2026-01-31","cited_by_count":13},{"id":"2309.10431","title":"Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions","created":"2023-09-19","cited_by_count":6},{"id":"2410.09886","title":"Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning","created":"2024-10-13","cited_by_count":5}],"next_cursor":null}