{"list":"other","total":64,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2306.07691","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","created":"2023-06-13","cited_by_count":152},{"id":"2006.08586","title":"Coherent Reconstruction of Multiple Humans from a Single Image","created":"2020-06-15","cited_by_count":136},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"2007.11678","title":"Contact and Human Dynamics from Monocular Video","created":"2020-07-22","cited_by_count":95},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2104.04045","title":"End-to-end speaker segmentation for overlap-aware resegmentation","created":"2021-04-08","cited_by_count":80},{"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},{"id":"2304.02419","title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","created":"2023-04-05","cited_by_count":76},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2202.05274","title":"Motion Puzzle: Arbitrary Motion Style Transfer by Body Part","created":"2022-02-10","cited_by_count":64},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2404.00299","title":"HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment","created":"2024-03-30","cited_by_count":53},{"id":"1906.04158","title":"Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction","created":"2019-06-10","cited_by_count":48},{"id":"2403.18811","title":"Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment","created":"2024-03-27","cited_by_count":47},{"id":"2503.01174","title":"Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics","created":"2025-03-03","cited_by_count":47},{"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},{"id":"2312.04547","title":"Digital Life Project: Autonomous 3D Characters with Social Intelligence","created":"2023-12-07","cited_by_count":43},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41},{"id":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40},{"id":"2503.13836","title":"SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing","created":"2025-03-18","cited_by_count":39},{"id":"2405.16273","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","created":"2024-05-25","cited_by_count":38},{"id":"2006.09888","title":"Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings","created":"2020-06-11","cited_by_count":36},{"id":"2404.05218","title":"Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning","created":"2024-04-08","cited_by_count":30},{"id":"2404.00368","title":"Towards Variable and Coordinated Holistic Co-Speech Motion Generation","created":"2024-03-30","cited_by_count":29},{"id":"2502.20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation","created":"2025-02-27","cited_by_count":28},{"id":"2303.05095","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","created":"2023-03-09","cited_by_count":26},{"id":"2210.11940","title":"JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking","created":"2022-10-20","cited_by_count":25},{"id":"2403.02090","title":"Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations","created":"2024-03-04","cited_by_count":18},{"id":"2403.06225","title":"MoST: Motion Style Transformer between Diverse Action Contents","created":"2024-03-10","cited_by_count":18},{"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},{"id":"2304.11293","title":"Nonverbal Cues in Human-Robot Interaction: A Communication Studies Perspective","created":"2023-04-22","cited_by_count":16},{"id":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14},{"id":"2209.12890","title":"It Takes Two: Learning to Plan for Human-Robot Cooperative Carrying","created":"2022-09-26","cited_by_count":12},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12},{"id":"2410.16044","title":"Large Language Models Know What To Say But Not When To Speak","created":"2024-10-21","cited_by_count":11},{"id":"2205.05177","title":"ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild","created":"2022-05-10","cited_by_count":10},{"id":"2212.05286","title":"A Survey of Multi-Agent Human-Robot Interaction Systems","created":"2022-12-10","cited_by_count":10},{"id":"2504.04010","title":"DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion","created":"2025-04-05","cited_by_count":10},{"id":"2505.21043","title":"Visual Cues Enhance Predictive Turn-Taking for Two-Party Human Interaction","created":"2025-05-27","cited_by_count":8},{"id":"2410.05628","title":"A Unified Framework for Motion Reasoning and Generation in Human Interaction","created":"2024-10-08","cited_by_count":5},{"id":"2407.06094","title":"ERR@HRI 2024 Challenge: Multimodal Detection of Errors and Failures in Human-Robot Interactions","created":"2024-07-08","cited_by_count":4}],"next_cursor":null}