{"list":"other","total":64,"rows":[{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"2212.06135","title":"Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion","created":"2022-12-12","cited_by_count":309},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"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":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"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":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"2404.15121","title":"Taming Diffusion Probabilistic Models for Character Control","created":"2024-04-23","cited_by_count":57},{"id":"2105.02451","title":"Learning Skeletal Articulations with Neural Blend Shapes","created":"2021-05-06","cited_by_count":53},{"id":"2103.15545","title":"Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models","created":"2021-03-29","cited_by_count":51},{"id":"2502.09615","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets","created":"2025-02-13","cited_by_count":47},{"id":"2504.12451","title":"One Model to Rig Them All: Diverse Skeleton Rigging with UniRig","created":"2025-04-16","cited_by_count":45},{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43},{"id":"2502.17327","title":"AnyTop: Character Animation Diffusion with Any Topology","created":"2025-02-24","cited_by_count":41},{"id":"2603.15546","title":"Kimodo: Scaling Controllable Human Motion Generation","created":"2026-03-16","cited_by_count":37},{"id":"2503.09631","title":"V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video","created":"2025-03-11","cited_by_count":33},{"id":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33},{"id":"2506.09982","title":"AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation","created":"2025-06-11","cited_by_count":32},{"id":"2406.06508","title":"Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer","created":"2024-06-10","cited_by_count":31},{"id":"2605.15187","title":"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation","created":"2026-05-14","cited_by_count":30},{"id":"2505.19377","title":"Absolute Coordinates Make Motion Generation Easy","created":"2025-05-26","cited_by_count":29},{"id":"2312.13604","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos","created":"2023-12-21","cited_by_count":21},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21},{"id":"2311.18303","title":"OmniMotionGPT: Animal Motion Generation with Limited Data","created":"2023-11-30","cited_by_count":20},{"id":"2503.19557","title":"Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion","created":"2025-03-25","cited_by_count":16},{"id":"2506.19851","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","created":"2025-06-24","cited_by_count":15},{"id":"2601.14253","title":"Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis","created":"2026-01-20","cited_by_count":15},{"id":"2506.07489","title":"Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video","created":"2025-06-09","cited_by_count":12},{"id":"2401.06146","title":"AAMDM: Accelerated Auto-regressive Motion Diffusion Model","created":"2023-12-02","cited_by_count":10},{"id":"2512.10881","title":"MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos","created":"2025-12-11","cited_by_count":10},{"id":"2412.05161","title":"DNF: Unconditional 4D Generation with Dictionary-based Neural Fields","created":"2024-12-06","cited_by_count":8},{"id":"2512.14133","title":"AnimaMimic: Imitating 3D Animation from Video Priors","created":"2025-12-16","cited_by_count":7},{"id":"2511.07409","title":"DIMO: Diverse 3D Motion Generation for Arbitrary Objects","created":"2025-11-10","cited_by_count":6},{"id":"2503.04257","title":"How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects","created":"2025-03-06","cited_by_count":5},{"id":"2603.15975","title":"UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors","created":"2026-03-16","cited_by_count":5},{"id":"2602.18873","title":"BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation","created":"2026-02-21","cited_by_count":4},{"id":"2601.07272","title":"PALUM: Part-based Attention Learning for Unified Motion Retargeting","created":"2026-01-12","cited_by_count":3},{"id":"2604.17623","title":"ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes","created":"2026-04-19","cited_by_count":3}],"next_cursor":null}