{"total":150,"rows":[{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357,"area":"diffusion"},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255,"area":"diffusion"},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223,"area":"diffusion"},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206,"area":"diffusion"},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168,"area":"diffusion"},{"id":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109,"area":"diffusion"},{"id":"2312.15004","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","created":"2023-12-22","cited_by_count":106,"area":"diffusion"},{"id":"2312.11994","title":"Optimizing Diffusion Noise Can Serve As Universal Motion Priors","created":"2023-12-19","cited_by_count":98,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2407.15138","title":"D$^4$M: Dataset Distillation via Disentangled Diffusion Model","created":"2024-07-21","cited_by_count":77,"area":"diffusion"},{"id":"2405.11126","title":"Flexible Motion In-betweening with Diffusion Models","created":"2024-05-17","cited_by_count":71,"area":"diffusion"},{"id":"2404.13040","title":"Analysis of Classifier-Free Guidance Weight Schedulers","created":"2024-04-19","cited_by_count":68,"area":"diffusion"},{"id":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67,"area":"diffusion"},{"id":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64,"area":"diffusion"},{"id":"2403.17827","title":"DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions","created":"2024-03-26","cited_by_count":62,"area":"diffusion"},{"id":"2404.15121","title":"Taming Diffusion Probabilistic Models for Character Control","created":"2024-04-23","cited_by_count":57,"area":"diffusion"},{"id":"2405.05691","title":"StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework","created":"2024-05-09","cited_by_count":50,"area":"diffusion"},{"id":"2312.02702","title":"Neural Sign Actors: A diffusion model for 3D sign language production from text","created":"2023-12-05","cited_by_count":49,"area":"diffusion"},{"id":"2403.11208","title":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention","created":"2024-03-17","cited_by_count":46,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43,"area":"diffusion"},{"id":"2310.02242","title":"Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models","created":"2023-10-03","cited_by_count":43,"area":"diffusion"},{"id":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","cited_by_count":42,"area":"diffusion"},{"id":"2312.04466","title":"Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","created":"2023-12-07","cited_by_count":39,"area":"diffusion"},{"id":"2503.13836","title":"SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing","created":"2025-03-18","cited_by_count":39,"area":"diffusion"},{"id":"2312.08895","title":"Motion Flow Matching for Human Motion Synthesis and Editing","created":"2023-12-14","cited_by_count":38,"area":"diffusion"},{"id":"2410.10780","title":"MaskControl: Spatio-Temporal Control for Masked Motion Synthesis","created":"2024-10-14","cited_by_count":38,"area":"diffusion"},{"id":"2309.01372","title":"DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion","created":"2023-09-04","cited_by_count":37,"area":"diffusion"},{"id":"2407.12783","title":"SMooDi: Stylized Motion Diffusion Model","created":"2024-07-17","cited_by_count":37,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2502.06805","title":"Efficient Diffusion Models: A Survey","created":"2025-02-03","cited_by_count":35,"area":"diffusion"},{"id":"2410.07296","title":"ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model","created":"2024-10-09","cited_by_count":26,"area":"diffusion"},{"id":"2407.14502","title":"M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models","created":"2024-07-19","cited_by_count":24,"area":"diffusion"},{"id":"2311.15864","title":"InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint","created":"2023-11-27","cited_by_count":23,"area":"diffusion"},{"id":"2401.02142","title":"GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation","created":"2024-01-04","cited_by_count":22,"area":"diffusion"},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22,"area":"diffusion"},{"id":"2409.09300","title":"ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion","created":"2024-09-14","cited_by_count":21,"area":"diffusion"},{"id":"2411.19527","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","created":"2024-11-29","cited_by_count":19,"area":"diffusion"},{"id":"2402.05712","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer","created":"2024-02-08","cited_by_count":18,"area":"diffusion"},{"id":"2405.03485","title":"LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model","created":"2024-05-06","cited_by_count":18,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2312.10993","title":"Realistic Human Motion Generation with Cross-Diffusion Models","created":"2023-12-18","cited_by_count":17,"area":"diffusion"},{"id":"2409.10473","title":"MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion","created":"2024-09-16","cited_by_count":15,"area":"diffusion"},{"id":"2506.19851","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models","created":"2025-06-24","cited_by_count":15,"area":"diffusion"},{"id":"2312.04867","title":"HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models","created":"2023-12-08","cited_by_count":13,"area":"diffusion"},{"id":"2312.10960","title":"Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model","created":"2023-12-18","cited_by_count":13,"area":"diffusion"},{"id":"2412.15664","title":"SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control","created":"2024-12-20","cited_by_count":13,"area":"diffusion"},{"id":"2412.20657","title":"Diffgrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model","created":"2024-12-30","cited_by_count":13,"area":"diffusion"},{"id":"2504.01019","title":"MixerMDM: Learnable Composition of Human Motion Diffusion Models","created":"2025-04-01","cited_by_count":13,"area":"diffusion"},{"id":"2512.18814","title":"EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer","created":"2025-12-21","cited_by_count":13,"area":"diffusion"},{"id":"2301.10134","title":"Bipartite Graph Diffusion Model for Human Interaction Generation","created":"2023-01-24","cited_by_count":11,"area":"diffusion"},{"id":"2305.13773","title":"Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis","created":"2023-05-23","cited_by_count":10,"area":"diffusion"},{"id":"2401.11115","title":"MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation","created":"2024-01-20","cited_by_count":10,"area":"diffusion"},{"id":"2407.10528","title":"Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation","created":"2024-07-15","cited_by_count":10,"area":"diffusion"},{"id":"2407.11532","title":"Length-Aware Motion Synthesis via Latent Diffusion","created":"2024-07-16","cited_by_count":10,"area":"diffusion"},{"id":"2501.19083","title":"MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model","created":"2025-01-31","cited_by_count":10,"area":"diffusion"},{"id":"2602.22594","title":"Causal Motion Diffusion Models for Autoregressive Motion Generation","created":"2026-02-26","cited_by_count":10,"area":"diffusion"},{"id":"2406.01867","title":"MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training","created":"2024-06-04","cited_by_count":9,"area":"diffusion"},{"id":"2410.14508","title":"LEAD: Latent Realignment for Human Motion Diffusion","created":"2024-10-18","cited_by_count":9,"area":"diffusion"},{"id":"2411.10745","title":"Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition","created":"2024-11-16","cited_by_count":9,"area":"diffusion"},{"id":"2506.02452","title":"ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model","created":"2025-06-03","cited_by_count":9,"area":"diffusion"},{"id":"2507.19292","title":"PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups","created":"2025-07-25","cited_by_count":9,"area":"diffusion"},{"id":"2409.19686","title":"Text-driven Human Motion Generation with Motion Masked Diffusion Model","created":"2024-09-29","cited_by_count":8,"area":"diffusion"},{"id":"2411.16964","title":"MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning","created":"2024-11-25","cited_by_count":8,"area":"diffusion"},{"id":"2505.17860","title":"Multi-Person Interaction Generation from Two-Person Motion Priors","created":"2025-05-23","cited_by_count":8,"area":"diffusion"},{"id":"2506.08541","title":"TrajFlow: Multi-modal Motion Prediction via Flow Matching","created":"2025-06-10","cited_by_count":8,"area":"diffusion"},{"id":"2308.10187","title":"Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks","created":"2023-08-20","cited_by_count":7,"area":"diffusion"},{"id":"2309.03031","title":"MCM: Multi-condition Motion Synthesis Framework for Multi-scenario","created":"2023-09-06","cited_by_count":7,"area":"diffusion"},{"id":"2409.11920","title":"Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models","created":"2024-09-18","cited_by_count":7,"area":"diffusion"},{"id":"2503.16973","title":"ARFlow: Human Action-Reaction Flow Matching with Physical Guidance","created":"2025-03-21","cited_by_count":7,"area":"diffusion"},{"id":"2503.21775","title":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2602.23165","title":"DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation","created":"2026-02-26","cited_by_count":7,"area":"diffusion"},{"id":"2312.12227","title":"HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback","created":"2023-12-19","cited_by_count":6,"area":"diffusion"},{"id":"2403.17213","title":"AnimateMe: 4D Facial Expressions via Diffusion Models","created":"2024-03-25","cited_by_count":6,"area":"diffusion"},{"id":"2405.03803","title":"MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization","created":"2024-05-06","cited_by_count":6,"area":"diffusion"},{"id":"2412.16670","title":"Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer","created":"2024-12-21","cited_by_count":6,"area":"diffusion"},{"id":"2501.05680","title":"EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion Models","created":"2025-01-10","cited_by_count":6,"area":"diffusion"},{"id":"2512.19692","title":"Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models","created":"2025-12-22","cited_by_count":6,"area":"diffusion"},{"id":"2403.02905","title":"MMoFusion: Multi-modal Co-Speech Motion Generation with Diffusion Model","created":"2024-03-05","cited_by_count":5,"area":"diffusion"},{"id":"2501.01449","title":"LS-GAN: Human Motion Synthesis with Latent-space GANs","created":"2024-12-30","cited_by_count":5,"area":"diffusion"},{"id":"2309.00199","title":"Diffusion Model with Clustering-based Conditioning for Food Image Generation","created":"2023-09-01","cited_by_count":4,"area":"diffusion"},{"id":"2312.02772","title":"FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions","created":"2023-12-05","cited_by_count":4,"area":"diffusion"},{"id":"2312.07133","title":"LatentMan: Generating Consistent Animated Characters using Image Diffusion Models","created":"2023-12-12","cited_by_count":4,"area":"diffusion"},{"id":"2504.01338","title":"FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation","created":"2025-04-02","cited_by_count":4,"area":"diffusion"},{"id":"2504.09885","title":"Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis","created":"2025-04-14","cited_by_count":4,"area":"diffusion"},{"id":"2505.00515","title":"Safety-Critical Traffic Simulation with Guided Latent Diffusion Model","created":"2025-05-01","cited_by_count":4,"area":"diffusion"},{"id":"2509.04058","title":"SMooGPT: Stylized Motion Generation using Large Language Models","created":"2025-09-04","cited_by_count":4,"area":"diffusion"},{"id":"2510.19789","title":"OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation","created":"2025-10-22","cited_by_count":4,"area":"diffusion"},{"id":"2603.16188","title":"ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion Control","created":"2026-03-17","cited_by_count":4,"area":"diffusion"},{"id":"2603.19227","title":"Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2603.26553","title":"SemConFlow: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching","created":"2026-03-27","cited_by_count":4,"area":"diffusion"},{"id":"2604.23264","title":"MotionHiFlow: Text-to-motion via hierarchical flow matching","created":"2026-04-25","cited_by_count":4,"area":"diffusion"},{"id":"2405.06778","title":"Shape Conditioned Human Motion Generation with Diffusion Model","created":"2024-05-10","cited_by_count":3,"area":"diffusion"},{"id":"2409.20502","title":"COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models","created":"2024-09-30","cited_by_count":3,"area":"diffusion"},{"id":"2411.16216","title":"SMGDiff: Soccer Motion Generation using diffusion probabilistic models","created":"2024-11-25","cited_by_count":3,"area":"diffusion"},{"id":"2503.09942","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers","created":"2025-03-13","cited_by_count":3,"area":"diffusion"}],"next_cursor":"100"}