{"list":"other","total":51,"rows":[{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2008.08465","title":"CosyPose: Consistent multi-view multi-object 6D pose estimation","created":"2020-08-19","cited_by_count":287},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148},{"id":"1612.00197","title":"Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses","created":"2016-12-01","cited_by_count":97},{"id":"1901.04111","title":"Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views","created":"2019-01-14","cited_by_count":83},{"id":"2509.25164","title":"YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection","created":"2025-09-29","cited_by_count":79},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68},{"id":"2401.10232","title":"ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions","created":"2024-01-18","cited_by_count":57},{"id":"2404.00299","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","created":"2024-03-30","cited_by_count":53},{"id":"2104.13542","title":"STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation","created":"2021-04-28","cited_by_count":47},{"id":"1801.02854","title":"Riemannian Motion Policies","created":"2018-01-09","cited_by_count":46},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2502.20323","title":"ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model","created":"2025-02-27","cited_by_count":29},{"id":"2512.11130","title":"Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching","created":"2025-12-11","cited_by_count":28},{"id":"2412.16490","title":"BODex: Scalable and Efficient Robotic Dexterous Grasp Synthesis Using Bilevel Optimization","created":"2024-12-21","cited_by_count":20},{"id":"2603.11633","title":"MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation","created":"2026-03-12","cited_by_count":19},{"id":"2108.06038","title":"Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration","created":"2021-08-13","cited_by_count":17},{"id":"2311.12943","title":"InteRACT: Transformer Models for Human Intent Prediction Conditioned on Robot Actions","created":"2023-11-21","cited_by_count":11},{"id":"2402.18796","title":"MOSAIC: Modular Foundation Models for Assistive and Interactive Cooking","created":"2024-02-29","cited_by_count":9},{"id":"2509.06953","title":"Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments","created":"2025-09-08","cited_by_count":9},{"id":"2506.14968","title":"FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization","created":"2025-06-17","cited_by_count":7},{"id":"2404.01402","title":"ContactHandover: Contact-Guided Robot-to-Human Object Handover","created":"2024-04-01","cited_by_count":3},{"id":"2505.10239","title":"Context-aware collaborative pushing of heavy objects using skeleton-based intention prediction","created":"2025-05-15","cited_by_count":3},{"id":"1709.03211","title":"A Nonparametric Motion Flow Model for Human Robot Cooperation","created":"2017-09-11","cited_by_count":2},{"id":"2502.12602","title":"Learning-based Dynamic Robot-to-Human Handover","created":"2025-02-18","cited_by_count":1}],"next_cursor":null}