{"total":206,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238,"area":null},{"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":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"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":"2404.00562","title":"Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction","created":"2024-03-31","cited_by_count":86,"area":null},{"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,"area":null},{"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,"area":null},{"id":"2405.11126","title":"Flexible Motion In-betweening with Diffusion Models","created":"2024-05-17","cited_by_count":71,"area":"diffusion"},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68,"area":null},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65,"area":null},{"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":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2404.00299","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","created":"2024-03-30","cited_by_count":53,"area":null},{"id":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47,"area":null},{"id":"2403.18811","title":"Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment","created":"2024-03-27","cited_by_count":47,"area":null},{"id":"2410.10010","title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling","created":"2024-10-13","cited_by_count":47,"area":null},{"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":"2406.14558","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","created":"2024-06-20","cited_by_count":44,"area":null},{"id":"2506.12479","title":"AI Flow: Perspectives, Scenarios, and Approaches","created":"2025-06-14","cited_by_count":44,"area":null},{"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":"2312.04547","title":"Digital Life Project: Autonomous 3D Characters with Social Intelligence","created":"2023-12-07","cited_by_count":43,"area":null},{"id":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42,"area":null},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40,"area":null},{"id":"2311.11243","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort","created":"2023-11-19","cited_by_count":38,"area":null},{"id":"2407.12371","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32,"area":null},{"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,"area":"diffusion"},{"id":"2404.09988","title":"in2IN: Leveraging individual Information to Generate Human INteractions","created":"2024-04-15","cited_by_count":29,"area":null},{"id":"2405.18483","title":"Towards Open Domain Text-Driven Synthesis of Multi-Person Motions","created":"2024-05-28","cited_by_count":29,"area":null},{"id":"2412.14172","title":"Learning from Massive Human Videos for Universal Humanoid Pose Control","created":"2024-12-18","cited_by_count":29,"area":null},{"id":"2505.19377","title":"Absolute Coordinates Make Motion Generation Easy","created":"2025-05-26","cited_by_count":29,"area":null},{"id":"2403.17422","title":"InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion","created":"2024-03-26","cited_by_count":28,"area":"diffusion"},{"id":"2502.20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation","created":"2025-02-27","cited_by_count":28,"area":null},{"id":"2312.08983","title":"Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting","created":"2023-12-14","cited_by_count":27,"area":null},{"id":"2408.17135","title":"TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation","created":"2024-08-30","cited_by_count":27,"area":null},{"id":"2503.18211","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","created":"2025-03-23","cited_by_count":27,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2503.20172","title":"Guiding Human-Object Interactions with Rich Geometry and Relations","created":"2025-03-26","cited_by_count":24,"area":null},{"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":"2406.00456","title":"Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation","created":"2024-06-01","cited_by_count":23,"area":"rag"},{"id":"2408.14765","title":"CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis","created":"2024-08-27","cited_by_count":23,"area":"diffusion"},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"area":null},{"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":"2506.18680","title":"DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling","created":"2025-06-23","cited_by_count":21,"area":null},{"id":"2508.02106","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis","created":"2025-08-04","cited_by_count":20,"area":null},{"id":"2311.04811","title":"Image-Based Virtual Try-On: A Survey","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2404.11291","title":"Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption","created":"2024-04-17","cited_by_count":19,"area":"diffusion"},{"id":"2404.01081","title":"PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation","created":"2024-04-01","cited_by_count":18,"area":null},{"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":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"area":null},{"id":"2404.04890","title":"A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16,"area":"ssm"},{"id":"2410.07757","title":"MMHead: Towards Fine-grained Multi-modal 3D Facial Animation","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2503.01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2306.14153","title":"DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data","created":"2023-06-25","cited_by_count":15,"area":"diffusion"},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2410.10790","title":"Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes","created":"2024-10-14","cited_by_count":14,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2412.20104","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","created":"2024-12-28","cited_by_count":14,"area":null},{"id":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14,"area":null},{"id":"2507.01390","title":"FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases","created":"2025-07-02","cited_by_count":14,"area":null},{"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":"2412.15664","title":"SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control","created":"2024-12-20","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":"2503.16801","title":"Auto-Regressive Diffusion for Generating 3D Human-Object Interactions","created":"2025-03-21","cited_by_count":12,"area":null},{"id":"2510.06504","title":"Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation","created":"2025-10-07","cited_by_count":11,"area":null},{"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,"area":null},{"id":"2602.22594","title":"Causal Motion Diffusion Models for Autoregressive Motion Generation","created":"2026-02-26","cited_by_count":10,"area":"diffusion"},{"id":"2409.04440","title":"Synergy and Synchrony in Couple Dances","created":"2024-09-06","cited_by_count":9,"area":null},{"id":"2503.04829","title":"StickMotion: Generating 3D Human Motions by Drawing a Stickman","created":"2025-03-05","cited_by_count":9,"area":null},{"id":"2505.01746","title":"Co$^{3}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion","created":"2025-05-03","cited_by_count":9,"area":null},{"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":"2404.14745","title":"You Think, You ACT: The New Task of Arbitrary Text to Motion Generation","created":"2024-04-23","cited_by_count":8,"area":null},{"id":"2411.04079","title":"Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generation","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2505.17860","title":"Multi-Person Interaction Generation from Two-Person Motion Priors","created":"2025-05-23","cited_by_count":8,"area":"diffusion"},{"id":"2507.05419","title":"Motion Generation: A Survey of Generative Approaches and Benchmarks","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2508.04681","title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","created":"2025-08-06","cited_by_count":8,"area":null},{"id":"2510.05097","title":"Pulp Motion: Framing-aware multimodal camera and human motion generation","created":"2025-10-06","cited_by_count":8,"area":null},{"id":"2312.07937","title":"BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics","created":"2023-12-13","cited_by_count":7,"area":null},{"id":"2402.04768","title":"Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interaction","created":"2024-02-07","cited_by_count":7,"area":null},{"id":"2403.11237","title":"FORCE: Physics-aware Human-object Interaction","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2503.13120","title":"3D Human Interaction Generation: A Survey","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2503.16451","title":"Think-Then-React: Towards Unconstrained Human Action-to-Reaction Generation","created":"2025-02-19","cited_by_count":7,"area":"lr"},{"id":"2503.16973","title":"ARFlow: Human Action-Reaction Flow Matching with Physical Guidance","created":"2025-03-21","cited_by_count":7,"area":"diffusion"},{"id":"2506.15483","title":"GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects","created":"2025-06-18","cited_by_count":7,"area":"diffusion"},{"id":"2508.03343","title":"WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval","created":"2025-08-05","cited_by_count":7,"area":null},{"id":"2510.14976","title":"Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation","created":"2025-10-16","cited_by_count":7,"area":null},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7,"area":null},{"id":"2405.03689","title":"Pose Priors from Language Models","created":"2024-05-06","cited_by_count":6,"area":null},{"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":"2503.14919","title":"GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2506.19840","title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","created":"2025-06-24","cited_by_count":6,"area":"diffusion"},{"id":"2508.17342","title":"DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions","created":"2025-08-24","cited_by_count":6,"area":null},{"id":"2509.24099","title":"Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow","created":"2025-09-28","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":"2603.25734","title":"Unleashing Guidance Without Classifiers for Human-Object Interaction Animation","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2404.05490","title":"Two-Person Interaction Augmentation with Skeleton Priors","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2506.10574","title":"DanceChat: Large Language Model-Guided Music-to-Dance Generation","created":"2025-06-12","cited_by_count":5,"area":null}],"next_cursor":"100"}