{"list":"other","total":56,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"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":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"1710.06542","title":"Asymmetric Actor Critic for Image-Based Robot Learning","created":"2017-10-18","cited_by_count":238},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189},{"id":"2508.08241","title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","created":"2025-08-11","cited_by_count":165},{"id":"2409.04410","title":"Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation","created":"2024-09-06","cited_by_count":155},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2502.01143","title":"ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills","created":"2025-02-03","cited_by_count":130},{"id":"2310.04582","title":"Universal Humanoid Motion Representations for Physics-Based Control","created":"2023-10-06","cited_by_count":116},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116},{"id":"2505.02833","title":"TWIST: Teleoperated Whole-Body Imitation System","created":"2025-05-05","cited_by_count":101},{"id":"2305.02195","title":"CALM: Conditional Adversarial Latent Models for Directable Virtual Characters","created":"2023-05-02","cited_by_count":94},{"id":"2410.21229","title":"HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots","created":"2024-10-28","cited_by_count":91},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85},{"id":"2506.14770","title":"GMT: General Motion Tracking for Humanoid Whole-Body Control","created":"2025-06-17","cited_by_count":83},{"id":"2502.13013","title":"HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit","created":"2025-02-18","cited_by_count":76},{"id":"2510.02252","title":"Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking","created":"2025-10-02","cited_by_count":75},{"id":"2505.03738","title":"AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control","created":"2025-05-06","cited_by_count":51},{"id":"2505.01425","title":"GENMO: A GENeralist Model for Human MOtion","created":"2025-05-02","cited_by_count":49},{"id":"2502.08378","title":"Learning Humanoid Standing-up Control across Diverse Postures","created":"2025-02-12","cited_by_count":46},{"id":"2011.15119","title":"UniCon: Universal Neural Controller For Physics-based Character Motion","created":"2020-11-30","cited_by_count":40},{"id":"2507.07356","title":"UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots","created":"2025-07-10","cited_by_count":37},{"id":"2509.13833","title":"Track Any Motions under Any Disturbances","created":"2025-09-17","cited_by_count":35},{"id":"2505.03728","title":"PyRoki: A Modular Toolkit for Robot Kinematic Optimization","created":"2025-05-06","cited_by_count":30},{"id":"2505.19377","title":"Absolute Coordinates Make Motion Generation Easy","created":"2025-05-26","cited_by_count":29},{"id":"2502.12152","title":"Learning Getting-Up Policies for Real-World Humanoid Robots","created":"2025-02-17","cited_by_count":26},{"id":"2509.13780","title":"Behavior Foundation Model for Humanoid Robots","created":"2025-09-17","cited_by_count":15},{"id":"2508.00097","title":"XRoboToolkit: A Cross-Platform Framework for Robot Teleoperation","created":"2025-07-31","cited_by_count":8}],"next_cursor":null}