{"list":"other","total":77,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"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":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2506.18871","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","created":"2025-06-23","cited_by_count":253},{"id":"2304.06140","title":"An Edit Friendly DDPM Noise Space: Inversion and Manipulations","created":"2023-04-12","cited_by_count":244},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","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":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"2410.03441","title":"CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control","created":"2024-10-04","cited_by_count":109},{"id":"2312.11994","title":"Optimizing Diffusion Noise Can Serve As Universal Motion Priors","created":"2023-12-19","cited_by_count":98},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2501.02487","title":"ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling","created":"2025-01-05","cited_by_count":95},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"id":"2312.06553","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","created":"2023-12-11","cited_by_count":93},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"id":"2510.08377","title":"UniVideo: Unified Understanding, Generation, and Editing for Videos","created":"2025-10-09","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":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72},{"id":"2405.11126","title":"Flexible Motion In-betweening with Diffusion Models","created":"2024-05-17","cited_by_count":71},{"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":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64},{"id":"2408.00712","title":"MotionFix: Text-Driven 3D Human Motion Editing","created":"2024-08-01","cited_by_count":64},{"id":"2404.15121","title":"Taming Diffusion Probabilistic Models for Character Control","created":"2024-04-23","cited_by_count":57},{"id":"2410.00086","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","created":"2024-09-30","cited_by_count":56},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2505.01425","title":"GENMO: A GENeralist Model for Human MOtion","created":"2025-05-02","cited_by_count":49},{"id":"2410.10010","title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling","created":"2024-10-13","cited_by_count":47},{"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":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42},{"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":"2410.10780","title":"MaskControl: Spatio-Temporal Control for Masked Motion Synthesis","created":"2024-10-14","cited_by_count":38},{"id":"2512.23464","title":"HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation","created":"2025-12-29","cited_by_count":36},{"id":"2403.13307","title":"LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment","created":"2024-03-20","cited_by_count":33},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32},{"id":"2510.08485","title":"InstructX: Towards Unified Visual Editing with MLLM Guidance","created":"2025-10-09","cited_by_count":32},{"id":"2502.02358","title":"MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm","created":"2025-02-04","cited_by_count":30},{"id":"2404.09988","title":"in2IN: Leveraging individual Information to Generate Human INteractions","created":"2024-04-15","cited_by_count":29},{"id":"2502.20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation","created":"2025-02-27","cited_by_count":28},{"id":"2503.18211","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","created":"2025-03-23","cited_by_count":27},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22},{"id":"2506.18680","title":"DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling","created":"2025-06-23","cited_by_count":21},{"id":"2410.18977","title":"Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing","created":"2024-10-24","cited_by_count":18},{"id":"2503.19557","title":"Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion","created":"2025-03-25","cited_by_count":16},{"id":"2512.16906","title":"VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization","created":"2025-12-18","cited_by_count":16},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2503.20724","title":"Dynamic Motion Blending for Versatile Motion Editing","created":"2025-03-26","cited_by_count":15},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12},{"id":"2503.16289","title":"SceneMI: Motion In-betweening for Modeling Human-Scene Interactions","created":"2025-03-20","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":"2602.12370","title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","created":"2026-02-12","cited_by_count":11},{"id":"2411.16964","title":"MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning","created":"2024-11-25","cited_by_count":8},{"id":"2510.14976","title":"Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation","created":"2025-10-16","cited_by_count":7},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7},{"id":"2506.19840","title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","created":"2025-06-24","cited_by_count":6},{"id":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6},{"id":"2512.24200","title":"PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation","created":"2025-12-30","cited_by_count":5},{"id":"2602.18432","title":"SARAH: Spatially Aware Real-time Agentic Humans","created":"2026-02-20","cited_by_count":2}],"next_cursor":null}