{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"id":"2401.00896","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","created":"2023-12-31","cited_by_count":91},{"id":"2505.07747","title":"Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets","created":"2025-05-12","cited_by_count":87},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71},{"id":"2406.07472","title":"4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models","created":"2024-06-11","cited_by_count":64},{"id":"2410.06756","title":"DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation","created":"2024-10-09","cited_by_count":58},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56},{"id":"2405.18132","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","created":"2024-05-28","cited_by_count":45},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45},{"id":"2412.15214","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","created":"2024-12-19","cited_by_count":39},{"id":"2603.15546","title":"Kimodo: Scaling Controllable Human Motion Generation","created":"2026-03-16","cited_by_count":37},{"id":"2303.15413","title":"Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation","created":"2023-03-27","cited_by_count":32},{"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":"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":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21},{"id":"2502.11697","title":"MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow","created":"2025-02-17","cited_by_count":17},{"id":"2601.16148","title":"ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion","created":"2026-01-22","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":"2104.00351","title":"TrajeVAE: Controllable Human Motion Generation from Trajectories","created":"2021-04-01","cited_by_count":14},{"id":"2504.01204","title":"Articulated Kinematics Distillation from Video Diffusion Models","created":"2025-04-01","cited_by_count":13},{"id":"2504.11389","title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","created":"2025-04-15","cited_by_count":13},{"id":"2410.00890","title":"Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation","created":"2024-10-01","cited_by_count":12},{"id":"2601.05251","title":"Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video","created":"2026-01-08","cited_by_count":12},{"id":"2508.07409","title":"CharacterShot: Controllable and Consistent 4D Character Animation","created":"2025-08-10","cited_by_count":9},{"id":"2504.00457","title":"Distilling Multi-view Diffusion Models into 3D Generators","created":"2025-04-01","cited_by_count":4},{"id":"2602.18873","title":"BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation","created":"2026-02-21","cited_by_count":4},{"id":"2604.26917","title":"AnimateAnyMesh++: A Flexible Feed-Forward Framework for High-Fidelity Text-Driven Mesh Animation","created":"2026-04-29","cited_by_count":4}],"next_cursor":null}