{"list":"other","total":106,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"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":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"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":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"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":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156},{"id":"2203.08528","title":"Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors","created":"2022-03-16","cited_by_count":146},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"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":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2207.13784","title":"AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing","created":"2022-07-27","cited_by_count":110},{"id":"1703.08014","title":"Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs","created":"2017-03-23","cited_by_count":109},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80},{"id":"2307.07511","title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","created":"2023-07-14","cited_by_count":78},{"id":"2203.15720","title":"Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generation","created":"2022-03-29","cited_by_count":76},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64},{"id":"2112.09251","title":"The Wanderings of Odysseus in 3D Scenes","created":"2021-12-16","cited_by_count":59},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2212.04360","title":"MIME: Human-Aware 3D Scene Generation","created":"2022-12-08","cited_by_count":57},{"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":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"2410.03187","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","created":"2024-10-04","cited_by_count":56},{"id":"2304.12518","title":"IMUPoser: Full-Body Pose Estimation using IMUs in Phones, Watches, and Earbuds","created":"2023-04-25","cited_by_count":54},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2309.07907","title":"Physically Plausible Full-Body Hand-Object Interaction Synthesis","created":"2023-09-14","cited_by_count":52},{"id":"2301.02667","title":"Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments","created":"2023-01-09","cited_by_count":51},{"id":"2505.01425","title":"GENMO: A GENeralist Model for Human MOtion","created":"2025-05-02","cited_by_count":49},{"id":"2506.09108","title":"SensorLM: Learning the Language of Wearable Sensors","created":"2025-06-10","cited_by_count":49},{"id":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45},{"id":"2012.10366","title":"Learning Complex 3D Human Self-Contact","created":"2020-12-18","cited_by_count":40},{"id":"2009.05224","title":"HAA500: Human-Centric Atomic Action Dataset with Curated Videos","created":"2020-09-11","cited_by_count":39},{"id":"2304.02061","title":"Generating Continual Human Motion in Diverse 3D Scenes","created":"2023-04-04","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":"2506.24086","title":"MotionGPT3: Human Motion as a Second Modality","created":"2025-06-30","cited_by_count":37},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32},{"id":"2308.16682","title":"DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion","created":"2023-08-31","cited_by_count":31},{"id":"2401.00847","title":"Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera","created":"2024-01-01","cited_by_count":31},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28},{"id":"2404.19619","title":"Physical Non-inertial Poser (PNP): Modeling Non-inertial Effects in Sparse-inertial Human Motion Capture","created":"2024-04-30","cited_by_count":24},{"id":"2504.12492","title":"MobilePoser: Real-Time Full-Body Pose Estimation and 3D Human Translation from IMUs in Mobile Consumer Devices","created":"2025-04-16","cited_by_count":23},{"id":"2112.03030","title":"Pose2Room: Understanding 3D Scenes from Human Activities","created":"2021-12-01","cited_by_count":22},{"id":"2410.03311","title":"Scaling Large Motion Models with Million-Level Human Motions","created":"2024-10-04","cited_by_count":22},{"id":"2301.01424","title":"Scene Synthesis from Human Motion","created":"2023-01-04","cited_by_count":20},{"id":"2412.06334","title":"TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions","created":"2024-12-09","cited_by_count":20},{"id":"2407.06628","title":"Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition","created":"2024-07-09","cited_by_count":18},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17},{"id":"2210.11795","title":"PoseScript: Linking 3D Human Poses and Natural Language","created":"2022-10-21","cited_by_count":14},{"id":"2505.05010","title":"Improving Global Motion Estimation in Sparse IMU-based Motion Capture with Physics","created":"2025-05-08","cited_by_count":12}],"next_cursor":"100"}