{"total":126,"rows":[{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184,"area":null},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"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":"2309.11306","title":"FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion","created":"2023-09-20","cited_by_count":78,"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":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2301.02667","title":"Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments","created":"2023-01-09","cited_by_count":51,"area":null},{"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":"2305.18891","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","created":"2023-05-30","cited_by_count":40,"area":null},{"id":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40,"area":null},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40,"area":null},{"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":"2403.06375","title":"FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization","created":"2024-03-11","cited_by_count":39,"area":null},{"id":"2301.10939","title":"Affective Faces for Goal-Driven Dyadic Communication","created":"2023-01-26","cited_by_count":35,"area":null},{"id":"2403.09069","title":"Dyadic Interaction Modeling for Social Behavior Generation","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2505.18096","title":"DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30,"area":null},{"id":"2303.05416","title":"FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning","created":"2023-03-09","cited_by_count":29,"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":"2405.18483","title":"Towards Open Domain Text-Driven Synthesis of Multi-Person Motions","created":"2024-05-28","cited_by_count":29,"area":null},{"id":"2406.14272","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","created":"2024-06-20","cited_by_count":28,"area":null},{"id":"2403.06363","title":"Say Anything with Any Style","created":"2024-03-11","cited_by_count":26,"area":null},{"id":"2512.22065","title":"StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars","created":"2025-12-26","cited_by_count":25,"area":"diffusion"},{"id":"2403.00274","title":"CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation","created":"2024-03-01","cited_by_count":22,"area":null},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22,"area":null},{"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":"2601.00664","title":"Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation","created":"2026-01-02","cited_by_count":19,"area":null},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18,"area":null},{"id":"2305.15748","title":"ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions","created":"2023-05-25","cited_by_count":17,"area":null},{"id":"2310.00068","title":"Emotional Listener Portrait: Neural Listener Head Generation with Emotion","created":"2023-09-29","cited_by_count":17,"area":null},{"id":"2302.06514","title":"Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?","created":"2023-02-13","cited_by_count":16,"area":null},{"id":"2401.05166","title":"REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge","created":"2024-01-10","cited_by_count":16,"area":null},{"id":"2507.00472","title":"ARIG: Autoregressive Interactive Head Generation for Real-time Conversations","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2311.18168","title":"Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2403.19467","title":"Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication","created":"2024-03-28","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":"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":"2209.12890","title":"It Takes Two: Learning to Plan for Human-Robot Cooperative Carrying","created":"2022-09-26","cited_by_count":12,"area":null},{"id":"2402.08086","title":"Text-centric Alignment for Multi-Modality Learning","created":"2024-02-12","cited_by_count":12,"area":null},{"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":"2305.15270","title":"Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2311.17465","title":"AgentAvatar: Disentangling Planning, Driving and Rendering for Photorealistic Avatar Agents","created":"2023-11-29","cited_by_count":11,"area":"agents"},{"id":"2512.09327","title":"UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking","created":"2025-12-10","cited_by_count":11,"area":null},{"id":"2504.04010","title":"DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion","created":"2025-04-05","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":"2505.17223","title":"REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2408.01826","title":"GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer","created":"2024-08-03","cited_by_count":8,"area":"diffusion"},{"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":"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":"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":"2305.11310","title":"AMII: Adaptive Multimodal Inter-personal and Intra-personal Model for Adapted Behavior Synthesis","created":"2023-05-18","cited_by_count":6,"area":null},{"id":"2309.08947","title":"Staged Contact-Aware Global Human Motion Forecasting","created":"2023-09-16","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":"2306.06583","title":"REACT2023: the first Multi-modal Multiple Appropriate Facial Reaction Generation Challenge","created":"2023-06-11","cited_by_count":5,"area":null},{"id":"2310.03205","title":"A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2505.21724","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2512.24408","title":"DyStream: Streaming Dyadic Talking Heads Generation via Flow Matching-based Autoregressive Model","created":"2025-12-30","cited_by_count":5,"area":"diffusion"},{"id":"2606.22905","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2307.09821","title":"Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline","created":"2023-07-19","cited_by_count":4,"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":"2407.15798","title":"Robust Facial Reactions Generation: An Emotion-Aware Framework with Modality Compensation","created":"2024-07-22","cited_by_count":4,"area":null},{"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":"2507.13942","title":"Frozen Forecasting: A Unified Evaluation","created":"2025-07-18","cited_by_count":4,"area":null},{"id":"2510.04712","title":"ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model","created":"2025-10-06","cited_by_count":4,"area":"diffusion"},{"id":"2308.06025","title":"Controlling Character Motions without Observable Driving Source","created":"2023-08-11","cited_by_count":3,"area":"driving"},{"id":"2505.07901","title":"Latent Behavior Diffusion for Sequential Reaction Generation in Dyadic Setting","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2510.21864","title":"LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2511.14223","title":"StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model","created":"2025-11-18","cited_by_count":3,"area":"diffusion"},{"id":"2512.15340","title":"Towards Seamless Interaction: Causal Turn-Level Modeling of Interactive 3D Conversational Head Dynamics","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2604.08125","title":"PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2307.02609","title":"MRecGen: Multimodal Appropriate Reaction Generator","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2310.07236","title":"AdaMesh: Personalized Facial Expressions and Head Poses for Adaptive Speech-Driven 3D Facial Animation","created":"2023-10-11","cited_by_count":2,"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":"2502.06822","title":"DiffListener: Discrete Diffusion Model for Listener Generation","created":"2025-02-05","cited_by_count":2,"area":"diffusion"},{"id":"2504.21718","title":"VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive Interaction","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2508.03050","title":"Multi-human Interactive Talking Dataset","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2509.05747","title":"InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios","created":"2025-09-06","cited_by_count":2,"area":null},{"id":"2601.10606","title":"RSATalker: Realistic Socially-Aware Talking Head Generation for Multi-Turn Conversation","created":"2026-01-15","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":"2605.28272","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","created":"2026-05-27","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":"2305.12369","title":"HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2307.10636","title":"Learning and Evaluating Human Preferences for Conversational Head Generation","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2406.00955","title":"How Video Meetings Change Your Expression","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2409.10848","title":"3DFacePolicy: Audio-Driven 3D Facial Animation Based on Action Control","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2502.08646","title":"Poly-Autoregressive Prediction for Modeling Interactions","created":"2025-02-12","cited_by_count":1,"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":"2504.20685","title":"Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2511.11473","title":"Proactive Hearing Assistants that Isolate Egocentric Conversations","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2601.01749","title":"MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2603.14794","title":"Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling","created":"2026-03-16","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":"2604.17211","title":"EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2606.31088","title":"Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2402.08837","title":"Learning to Generate Context-Sensitive Backchannel Smiles for Embodied AI Agents with Applications in Mental Health Dialogues","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2409.05089","title":"Leveraging WaveNet for Dynamic Listening Head Modeling from Speech","created":"2024-09-08","cited_by_count":0,"area":null},{"id":"2409.11635","title":"PainDiffusion: Learning to Express Pain","created":"2024-09-18","cited_by_count":0,"area":null}],"next_cursor":"100"}