{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"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":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"id":"2003.04583","title":"TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style","created":"2020-03-10","cited_by_count":149},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91},{"id":"2410.21229","title":"HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots","created":"2024-10-28","cited_by_count":91},{"id":"2210.08340","title":"Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution","created":"2022-10-15","cited_by_count":78},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78},{"id":"2509.26633","title":"OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction","created":"2025-09-30","cited_by_count":71},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67},{"id":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62},{"id":"2101.06571","title":"S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling","created":"2021-01-17","cited_by_count":59},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2404.05695","title":"Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer","created":"2024-04-08","cited_by_count":53},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40},{"id":"2409.20514","title":"Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation","created":"2024-09-30","cited_by_count":39},{"id":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","cited_by_count":34},{"id":"2203.14698","title":"LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds","created":"2022-03-28","cited_by_count":33},{"id":"2309.14225","title":"HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitation","created":"2023-09-25","cited_by_count":32},{"id":"2410.11825","title":"Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies","created":"2024-10-15","cited_by_count":30},{"id":"2412.14172","title":"Learning from Massive Human Videos for Universal Humanoid Pose Control","created":"2024-12-18","cited_by_count":29},{"id":"2303.17948","title":"CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions","created":"2023-03-31","cited_by_count":27},{"id":"2410.12773","title":"Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions","created":"2024-10-16","cited_by_count":23},{"id":"2403.19501","title":"RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method","created":"2024-03-28","cited_by_count":16},{"id":"2408.16426","title":"COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation","created":"2024-08-29","cited_by_count":15},{"id":"2505.18780","title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","created":"2025-05-24","cited_by_count":5},{"id":"2510.26236","title":"PHUMA: Physically Reliable Humanoid Locomotion Dataset","created":"2025-10-30","cited_by_count":5},{"id":"2107.02675","title":"Real-time Pose Estimation from Images for Multiple Humanoid Robots","created":"2021-07-06","cited_by_count":3},{"id":"2503.21268","title":"ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate","created":"2025-03-27","cited_by_count":3},{"id":"2204.11751","title":"Adversarial Attention for Human Motion Synthesis","created":"2022-04-25","cited_by_count":1}],"next_cursor":null}