{"total":105,"rows":[{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"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":"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":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26,"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":"2511.14394","title":"BEDLAM2.0: Synthetic Humans and Cameras in Motion","created":"2025-11-18","cited_by_count":25,"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":"2411.19527","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","created":"2024-11-29","cited_by_count":19,"area":"diffusion"},{"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":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14,"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":"2508.00599","title":"DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior","created":"2025-08-01","cited_by_count":13,"area":"diffusion"},{"id":"2408.06010","title":"DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation","created":"2024-08-12","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":"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":"2507.20562","title":"MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization","created":"2025-07-28","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":"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":"2507.22731","title":"GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation","created":"2025-07-30","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":"2603.03265","title":"DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction","created":"2026-03-03","cited_by_count":7,"area":null},{"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":"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":"2503.01175","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","created":"2025-03-03","cited_by_count":6,"area":null},{"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":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6,"area":"agents"},{"id":"2503.20218","title":"Video Motion Graphs","created":"2025-03-26","cited_by_count":5,"area":"diffusion"},{"id":"2602.18057","title":"Temporal Consistency-Aware Text-to-Motion Generation","created":"2026-02-20","cited_by_count":5,"area":null},{"id":"2605.22894","title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control","created":"2026-05-21","cited_by_count":5,"area":"diffusion"},{"id":"2506.00958","title":"Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues","created":"2025-06-01","cited_by_count":4,"area":null},{"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":"2604.11417","title":"Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech","created":"2026-04-13","cited_by_count":4,"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":"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":"2508.06205","title":"PA-HOI: A Physics-Aware Human and Object Interaction Dataset","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2510.14954","title":"OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2512.01189","title":"fMRI2GES: Co-speech Gesture Reconstruction from fMRI Signal with Dual Brain Decoding Alignment","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2512.12664","title":"InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation","created":"2025-12-14","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":"2606.19935","title":"PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation","created":"2026-06-18","cited_by_count":3,"area":null},{"id":"2409.19143","title":"Diverse Code Query Learning for Speech-Driven Facial Animation","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2503.03474","title":"Enhancing Spoken Discourse Modeling in Language Models Using Gestural Cues","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2503.10488","title":"Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2505.23120","title":"MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2510.12834","title":"Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2510.13208","title":"MimicParts: Part-aware Style Injection for Speech-Driven 3D Motion Generation","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2602.18432","title":"SARAH: Spatially Aware Real-time Agentic Humans","created":"2026-02-20","cited_by_count":2,"area":"agents"},{"id":"2602.23739","title":"U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2603.28766","title":"HandX: Scaling Bimanual Motion and Interaction Generation","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2603.29655","title":"Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.04395","title":"BiTDiff: Fine-Grained 3D Conducting Motion Generation via BiMamba-Transformer Diffusion","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2606.03874","title":"DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.01157","title":"InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2503.14040","title":"MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2506.16159","title":"Co-Speech Gesture and Facial Expression Generation for Non-Photorealistic 3D Characters","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2507.00792","title":"JAX-IK: Real-Time Inverse Kinematics for Generating Multi-Constrained Movements of Virtual Human Characters","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.04522","title":"Grounded Gesture Generation: Language, Motion, and Space","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2510.19350","title":"Modeling Turn-Taking with Semantically Informed Gestures","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2511.01233","title":"Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2601.03959","title":"FUSION: Full-Body Unified Motion Prior for Body and Hands via Diffusion","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.04236","title":"SmoothSync: Dual-Stream Diffusion Transformers for Jitter-Robust Beat-Synchronized Gesture Generation from Quantized Audio","created":"2026-01-04","cited_by_count":1,"area":"diffusion"},{"id":"2602.09534","title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.17770","title":"CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.15083","title":"ReactMotion: Generating Reactive Listener Motions from Speaker Utterance","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.07252","title":"PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.14731","title":"UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.26236","title":"DuoGesture: Motion-Grounded Semantic Conditioning and Biomechanical Beat Priors for Co-Speech Gesture Generation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.29488","title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2605.30256","title":"VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2605.30608","title":"Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.13630","title":"From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.10287","title":"InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2608.15296","title":"FMReward: Aligning and Evaluating Audio-Driven 3D Facial Animation with Human Preferences","created":"2026-08-15","cited_by_count":1,"area":"alignment"},{"id":"2609.00369","title":"Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2412.14333","title":"Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2503.21847","title":"ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2505.15058","title":"AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars","created":"2025-05-21","cited_by_count":0,"area":"diffusion"},{"id":"2505.21146","title":"IKMo: Image-Keyframed Motion Generation with Trajectory-Pose Conditioned Motion Diffusion Model","created":"2025-05-27","cited_by_count":0,"area":"diffusion"},{"id":"2510.02722","title":"MoGIC: Boosting Motion Generation via Intention Understanding and Visual Context","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.17617","title":"ImaGGen: Zero-Shot Generation of Co-Speech Semantic Gestures Grounded in Language and Image Input","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.02576","title":"Co-speech Gesture Video Generation via Motion-Based Graph Retrieval","created":"2025-12-02","cited_by_count":0,"area":"diffusion"},{"id":"2512.16081","title":"Evaluation of Generative Models for Emotional 3D Animation Generation in VR","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2604.12856","title":"PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.14953","title":"Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.15889","title":"SiGnature: Explicit Motion Diffusion for Stylized Semantic Gesture","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.20731","title":"XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.05733","title":"ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.01643","title":"StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.24909","title":"Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.25734","title":"InteractGesture: Progressive Chunk Guidance for Continuous Streaming Co-Speech Gesture Control","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04250","title":"Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.16011","title":"EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation","created":"2026-08-19","cited_by_count":0,"area":"diffusion"},{"id":"2609.33311","title":"SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36624","title":"DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36685","title":"When Semantics Matter: Reliability-Aware Semantic-Rhythm Control for Co-Speech Gesture Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38400","title":"GestAdapt: Workspace-Conditioned Co-Speech Gesture Generation for Humanoid Robots","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}