{"list":"other","total":74,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"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":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2310.02664","title":"On Memorization in Diffusion Models","created":"2023-10-04","cited_by_count":125},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113},{"id":"2310.00434","title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","created":"2023-09-30","cited_by_count":81},{"id":"2205.13600","title":"MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control","created":"2022-05-26","cited_by_count":80},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2311.03764","title":"Neuro-GPT: Towards A Foundation Model for EEG","created":"2023-11-07","cited_by_count":74},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2310.16046","title":"A Unified, Scalable Framework for Neural Population Decoding","created":"2023-10-24","cited_by_count":61},{"id":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60},{"id":"2003.01888","title":"MoVi: A Large Multipurpose Motion and Video Dataset","created":"2020-03-04","cited_by_count":58},{"id":"2408.10700","title":"AnyGraph: Graph Foundation Model in the Wild","created":"2024-08-20","cited_by_count":53},{"id":"2403.05618","title":"OmniJet-$\\alpha$: The first cross-task foundation model for particle physics","created":"2024-03-08","cited_by_count":43},{"id":"2008.06133","title":"3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View","created":"2020-08-13","cited_by_count":40},{"id":"2203.07436","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","created":"2022-03-14","cited_by_count":39},{"id":"2402.16412","title":"TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis","created":"2024-02-26","cited_by_count":39},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39},{"id":"2311.14379","title":"Robot Learning in the Era of Foundation Models: A Survey","created":"2023-11-24","cited_by_count":38},{"id":"2405.16273","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","created":"2024-05-25","cited_by_count":38},{"id":"2306.00576","title":"MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding","created":"2023-06-01","cited_by_count":36},{"id":"2502.03251","title":"RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry","created":"2025-02-05","cited_by_count":35},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29},{"id":"2404.15383","title":"WANDR: Intention-guided Human Motion Generation","created":"2024-04-23","cited_by_count":26},{"id":"2010.06449","title":"A review of 3D human pose estimation algorithms for markerless motion capture","created":"2020-10-13","cited_by_count":24},{"id":"2310.16447","title":"ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors","created":"2023-10-25","cited_by_count":24},{"id":"2412.17811","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models","created":"2024-12-23","cited_by_count":23},{"id":"2412.02725","title":"emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation","created":"2024-12-02","cited_by_count":22},{"id":"2405.10020","title":"Natural Language Can Help Bridge the Sim2Real Gap","created":"2024-05-16","cited_by_count":21},{"id":"2402.19229","title":"CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition","created":"2024-02-29","cited_by_count":19},{"id":"2409.16784","title":"World Model-based Perception for Visual Legged Locomotion","created":"2024-09-25","cited_by_count":18},{"id":"2501.07800","title":"BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos","created":"2025-01-14","cited_by_count":16},{"id":"2505.06166","title":"DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models","created":"2025-05-09","cited_by_count":16},{"id":"2503.18223","title":"MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps","created":"2025-03-23","cited_by_count":14},{"id":"2406.18537","title":"AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale","created":"2024-05-16","cited_by_count":11},{"id":"1907.10226","title":"Movement science needs different pose tracking algorithms","created":"2019-07-24","cited_by_count":10},{"id":"2503.14637","title":"KINESIS: Motion Imitation for Human Musculoskeletal Locomotion","created":"2025-03-18","cited_by_count":7},{"id":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","cited_by_count":6},{"id":"2309.12529","title":"Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution","created":"2023-09-21","cited_by_count":5},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5},{"id":"2303.08811","title":"Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis","created":"2023-03-15","cited_by_count":4}],"next_cursor":null}