{"list":"other","total":83,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"1808.10006","title":"Correcting Length Bias in Neural Machine Translation","created":"2018-08-29","cited_by_count":120},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2410.03441","title":"CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control","created":"2024-10-04","cited_by_count":109},{"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},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"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},{"id":"1904.09882","title":"You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions","created":"2019-04-22","cited_by_count":82},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2402.15509","title":"Seamless Human Motion Composition with Blended Positional Encodings","created":"2024-02-23","cited_by_count":80},{"id":"2309.06284","title":"Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model","created":"2023-09-12","cited_by_count":79},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67},{"id":"2403.13900","title":"CoMo: Controllable Motion Generation through Language Guided Pose Code Editing","created":"2024-03-20","cited_by_count":67},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"2403.18512","title":"ParCo: Part-Coordinating Text-to-Motion Synthesis","created":"2024-03-27","cited_by_count":55},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"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":"2501.18898","title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","created":"2025-01-31","cited_by_count":44},{"id":"2207.01685","title":"Interaction Transformer for Human Reaction Generation","created":"2022-07-04","cited_by_count":42},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35},{"id":"2410.00464","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","created":"2024-10-01","cited_by_count":35},{"id":"2412.16563","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","created":"2024-12-21","cited_by_count":32},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31},{"id":"2305.09381","title":"AMD: Autoregressive Motion Diffusion","created":"2023-05-16","cited_by_count":30},{"id":"2412.14706","title":"EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space","created":"2024-12-19","cited_by_count":30},{"id":"2504.02478","title":"MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities","created":"2025-04-03","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":"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},{"id":"2311.15864","title":"InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint","created":"2023-11-27","cited_by_count":23},{"id":"2411.15472","title":"KinMo: Kinematic-aware Human Motion Understanding and Generation","created":"2024-11-23","cited_by_count":21},{"id":"2502.05534","title":"Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation","created":"2025-02-08","cited_by_count":21},{"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},{"id":"2305.15748","title":"ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions","created":"2023-05-25","cited_by_count":17},{"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},{"id":"2401.05166","title":"REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge","created":"2024-01-10","cited_by_count":16},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2403.19467","title":"Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication","created":"2024-03-28","cited_by_count":14},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12},{"id":"2504.03639","title":"Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions","created":"2025-04-04","cited_by_count":11},{"id":"2512.09327","title":"UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking","created":"2025-12-10","cited_by_count":11},{"id":"2301.06690","title":"Audio2Gestures: Generating Diverse Gestures from Audio","created":"2023-01-17","cited_by_count":10},{"id":"2401.01382","title":"Exploring Multi-Modal Control in Music-Driven Dance Generation","created":"2024-01-01","cited_by_count":10},{"id":"2009.02041","title":"AIR-Act2Act: Human-human interaction dataset for teaching non-verbal social behaviors to robots","created":"2020-09-04","cited_by_count":9},{"id":"2503.04829","title":"StickMotion: Generating 3D Human Motions by Drawing a Stickman","created":"2025-03-05","cited_by_count":9},{"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},{"id":"2409.01522","title":"Lagrangian Motion Fields for Long-term Motion Generation","created":"2024-09-03","cited_by_count":5},{"id":"2505.21724","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","created":"2025-05-27","cited_by_count":5},{"id":"2510.04712","title":"ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model","created":"2025-10-06","cited_by_count":4},{"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}],"next_cursor":null}