{"list":"other","total":54,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"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":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"2410.17725","title":"YOLOv11: An Overview of the Key Architectural Enhancements","created":"2024-10-23","cited_by_count":425},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"1906.01140","title":"Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds","created":"2019-06-04","cited_by_count":156},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"2312.06553","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","created":"2023-12-11","cited_by_count":93},{"id":"1709.05448","title":"Learning Sampling Distributions for Robot Motion Planning","created":"2017-09-16","cited_by_count":82},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62},{"id":"2407.11385","title":"Omnigrasp: Grasping Diverse Objects with Simulated Humanoids","created":"2024-07-16","cited_by_count":46},{"id":"2205.12256","title":"Differentiable Dynamics for Articulated 3d Human Motion Reconstruction","created":"2022-05-24","cited_by_count":39},{"id":"2308.09421","title":"MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection","created":"2023-08-18","cited_by_count":33},{"id":"2203.00352","title":"Affordance Learning from Play for Sample-Efficient Policy Learning","created":"2022-03-01","cited_by_count":30},{"id":"2404.01491","title":"SUGAR: Pre-training 3D Visual Representations for Robotics","created":"2024-04-01","cited_by_count":26},{"id":"2507.05169","title":"Critique of World Model","created":"2025-07-07","cited_by_count":25},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7},{"id":"2505.16399","title":"Sketchy Bounding-box Supervision for 3D Instance Segmentation","created":"2025-05-22","cited_by_count":4},{"id":"2501.06047","title":"Learning Affordances from Interactive Exploration using an Object-level Map","created":"2025-01-10","cited_by_count":1}],"next_cursor":null}