{"total":158,"rows":[{"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":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109,"area":null},{"id":"2401.00374","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","created":"2023-12-31","cited_by_count":105,"area":null},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96,"area":null},{"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":"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":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82,"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":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2401.04747","title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","created":"2024-01-09","cited_by_count":62,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2403.10518","title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","created":"2024-03-15","cited_by_count":61,"area":null},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60,"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":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46,"area":"ssm"},{"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,"area":null},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41,"area":null},{"id":"2305.18891","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","created":"2023-05-30","cited_by_count":40,"area":null},{"id":"2405.09814","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","created":"2024-05-16","cited_by_count":40,"area":null},{"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":"2401.15687","title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","created":"2024-01-28","cited_by_count":39,"area":null},{"id":"2407.12783","title":"SMooDi: Stylized Motion Diffusion Model","created":"2024-07-17","cited_by_count":37,"area":"diffusion"},{"id":"2410.00464","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2410.04221","title":"TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation","created":"2024-10-05","cited_by_count":32,"area":null},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","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":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30,"area":null},{"id":"2404.00368","title":"Towards Variable and Coordinated Holistic Co-Speech Motion Generation","created":"2024-03-30","cited_by_count":29,"area":null},{"id":"2309.05455","title":"Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation","created":"2023-09-11","cited_by_count":28,"area":null},{"id":"2412.06786","title":"Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis","created":"2024-12-09","cited_by_count":26,"area":null},{"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":"2312.12634","title":"MotionScript: Natural Language Descriptions for Expressive 3D Human Motions","created":"2023-12-19","cited_by_count":21,"area":null},{"id":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21,"area":null},{"id":"2409.07649","title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","created":"2024-09-11","cited_by_count":20,"area":null},{"id":"2503.13130","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation","created":"2025-03-17","cited_by_count":20,"area":null},{"id":"2401.03476","title":"Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness","created":"2024-01-07","cited_by_count":18,"area":"diffusion"},{"id":"2402.16143","title":"Cinematographic Camera Diffusion Model","created":"2024-02-25","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":"2311.17532","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","created":"2023-11-29","cited_by_count":17,"area":null},{"id":"2504.09209","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","created":"2025-04-12","cited_by_count":17,"area":null},{"id":"2507.19359","title":"SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning","created":"2025-07-25","cited_by_count":17,"area":null},{"id":"2312.09767","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","created":"2023-12-15","cited_by_count":16,"area":"diffusion"},{"id":"2306.11496","title":"EMoG: Synthesizing Emotive Co-speech 3D Gesture with Diffusion Model","created":"2023-06-20","cited_by_count":15,"area":"diffusion"},{"id":"2309.07051","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","created":"2023-09-13","cited_by_count":15,"area":"diffusion"},{"id":"2408.02879","title":"Body of Her: A Preliminary Study on End-to-End Humanoid Agent","created":"2024-08-06","cited_by_count":15,"area":"agents"},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2306.09417","title":"Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis","created":"2023-06-15","cited_by_count":13,"area":null},{"id":"2403.01226","title":"DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction","created":"2024-03-02","cited_by_count":13,"area":null},{"id":"2409.07966","title":"ProbTalk3D: Non-Deterministic Emotion Controllable Speech-Driven 3D Facial Animation Synthesis Using VQ-VAE","created":"2024-09-12","cited_by_count":13,"area":null},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12,"area":null},{"id":"2511.10076","title":"Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints","created":"2025-11-13","cited_by_count":12,"area":null},{"id":"2507.20220","title":"Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2403.11469","title":"Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space","created":"2024-03-18","cited_by_count":10,"area":null},{"id":"2410.14508","title":"LEAD: Latent Realignment for Human Motion Diffusion","created":"2024-10-18","cited_by_count":9,"area":"diffusion"},{"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":"2603.03282","title":"MIBURI: Towards Expressive Interactive Gesture Synthesis","created":"2026-03-03","cited_by_count":9,"area":null},{"id":"2412.05161","title":"DNF: Unconditional 4D Generation with Dictionary-based Neural Fields","created":"2024-12-06","cited_by_count":8,"area":null},{"id":"2505.09379","title":"Text-driven Motion Generation: Overview, Challenges and Directions","created":"2025-05-14","cited_by_count":8,"area":null},{"id":"2505.23290","title":"Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2510.04637","title":"Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents","created":"2025-10-06","cited_by_count":8,"area":"agents"},{"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":"2405.06646","title":"Diffusion-based Human Motion Style Transfer with Semantic Guidance","created":"2024-03-20","cited_by_count":7,"area":"diffusion"},{"id":"2405.11690","title":"InterAct: Capture and Modelling of Realistic, Expressive and Interactive Activities between Two Persons in Daily Scenarios","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2408.03312","title":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation","created":"2024-08-06","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":"2605.06064","title":"PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2310.05181","title":"Unified speech and gesture synthesis using flow matching","created":"2023-10-08","cited_by_count":6,"area":"diffusion"},{"id":"2403.10805","title":"Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference","created":"2024-03-16","cited_by_count":6,"area":null},{"id":"2408.09397","title":"Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony","created":"2024-08-18","cited_by_count":6,"area":null},{"id":"2412.14484","title":"Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2312.12763","title":"AMD:Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2401.10889","title":"Synthesizing Moving People with 3D Control","created":"2024-01-19","cited_by_count":5,"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":"2404.19622","title":"Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2409.01522","title":"Lagrangian Motion Fields for Long-term Motion Generation","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2311.17425","title":"SpeechAct: Towards Generating Whole-body Motion from Speech","created":"2023-11-29","cited_by_count":4,"area":null},{"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":"2409.05387","title":"Decoupling Contact for Fine-Grained Motion Style Transfer","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2410.23836","title":"Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts","created":"2024-10-31","cited_by_count":4,"area":"moe"},{"id":"2511.22863","title":"CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation","created":"2025-11-28","cited_by_count":4,"area":null},{"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":"2604.02908","title":"SentiAvatar: Towards Expressive and Interactive Digital Humans","created":"2026-04-03","cited_by_count":4,"area":null},{"id":"2303.16856","title":"Robust Dancer: Long-term 3D Dance Synthesis Using Unpaired Data","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2404.19277","title":"Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion Model","created":"2024-04-30","cited_by_count":3,"area":"diffusion"},{"id":"2407.14296","title":"Foundation Models for Autonomous Robots in Unstructured Environments","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2410.00253","title":"MM-Conv: A Multi-modal Conversational Dataset for Virtual Humans","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2410.06327","title":"Towards a GENEA Leaderboard -- an Extended, Living Benchmark for Evaluating and Advancing Conversational Motion Synthesis","created":"2024-10-08","cited_by_count":3,"area":null},{"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"},{"id":"2503.17059","title":"DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech","created":"2025-03-21","cited_by_count":3,"area":"diffusion"},{"id":"2503.22668","title":"Understanding Co-speech Gestures in-the-wild","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2505.20056","title":"PAMD: Plausibility-Aware Motion Diffusion Model for Long Dance Generation","created":"2025-05-26","cited_by_count":3,"area":"diffusion"},{"id":"2602.06548","title":"NECromancer: Breathing Life into Skeletons via BVH Animation","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2602.14048","title":"ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interaction","created":"2026-02-15","cited_by_count":3,"area":"agents"},{"id":"2608.28693","title":"RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction","created":"2026-08-27","cited_by_count":3,"area":"diffusion"},{"id":"2308.15016","title":"C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model","created":"2023-08-29","cited_by_count":2,"area":"diffusion"}],"next_cursor":"100"}