{"list":"other","total":54,"rows":[{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"1805.06485","title":"QuaterNet: A Quaternion-based Recurrent Model for Human Motion","created":"2018-05-16","cited_by_count":109},{"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":"2410.05260","title":"DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control","created":"2024-10-07","cited_by_count":84},{"id":"2309.06284","title":"Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model","created":"2023-09-12","cited_by_count":79},{"id":"2507.15857","title":"Diffusion Beats Autoregressive in Data-Constrained Settings","created":"2025-07-21","cited_by_count":63},{"id":"2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","created":"2024-10-29","cited_by_count":59},{"id":"2403.18512","title":"ParCo: Part-Coordinating Text-to-Motion Synthesis","created":"2024-03-27","cited_by_count":55},{"id":"2403.19435","title":"BAMM: Bidirectional Autoregressive Motion Model","created":"2024-03-28","cited_by_count":55},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2511.03276","title":"Diffusion Language Models are Super Data Learners","created":"2025-11-05","cited_by_count":48},{"id":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46},{"id":"2311.01015","title":"Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs","created":"2023-11-02","cited_by_count":45},{"id":"2509.20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation","created":"2025-09-24","cited_by_count":41},{"id":"2309.01372","title":"DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion","created":"2023-09-04","cited_by_count":37},{"id":"2111.11739","title":"AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition","created":"2021-11-23","cited_by_count":36},{"id":"2405.18483","title":"Towards Open Domain Text-Driven Synthesis of Multi-Person Motions","created":"2024-05-28","cited_by_count":29},{"id":"2406.10797","title":"STAR: Scale-wise Text-conditioned AutoRegressive image generation","created":"2024-06-16","cited_by_count":28},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19},{"id":"2411.06307","title":"Acoustic Volume Rendering for Neural Impulse Response Fields","created":"2024-11-09","cited_by_count":14},{"id":"2503.07390","title":"PersonaBooth: Personalized Text-to-Motion Generation","created":"2025-03-10","cited_by_count":14},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12},{"id":"2509.21625","title":"Guiding Audio Editing with Audio Language Model","created":"2025-09-25","cited_by_count":12},{"id":"2504.03639","title":"Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions","created":"2025-04-04","cited_by_count":11},{"id":"2510.06504","title":"Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation","created":"2025-10-07","cited_by_count":11},{"id":"2508.12176","title":"Scalable RF Simulation in Generative 4D Worlds","created":"2025-08-16","cited_by_count":2}],"next_cursor":null}