{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"id":"2410.10733","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","created":"2024-10-14","cited_by_count":217},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2402.11411","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","created":"2024-02-18","cited_by_count":198},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"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":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2312.10665","title":"Silkie: Preference Distillation for Large Visual Language Models","created":"2023-12-17","cited_by_count":130},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90},{"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":"2305.04919","title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models","created":"2023-05-08","cited_by_count":85},{"id":"2001.09326","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","created":"2020-01-25","cited_by_count":84},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84},{"id":"2401.06838","title":"MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization","created":"2024-01-12","cited_by_count":69},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"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},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55},{"id":"2306.00416","title":"Interactive Character Control with Auto-Regressive Motion Diffusion Models","created":"2023-06-01","cited_by_count":55},{"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":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41},{"id":"2405.09814","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","created":"2024-05-16","cited_by_count":40},{"id":"2210.01448","title":"Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings","created":"2022-10-04","cited_by_count":38},{"id":"2302.08242","title":"Tuning computer vision models with task rewards","created":"2023-02-16","cited_by_count":37},{"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":"2412.06786","title":"Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis","created":"2024-12-09","cited_by_count":26},{"id":"2506.18680","title":"DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling","created":"2025-06-23","cited_by_count":21},{"id":"2405.13336","title":"SIGGesture: Generalized Co-Speech Gesture Synthesis via Semantic Injection with Large-Scale Pre-Training Diffusion Models","created":"2024-05-22","cited_by_count":18},{"id":"2306.00378","title":"Example-based Motion Synthesis via Generative Motion Matching","created":"2023-06-01","cited_by_count":16},{"id":"2309.07051","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","created":"2023-09-13","cited_by_count":15},{"id":"2412.20104","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","created":"2024-12-28","cited_by_count":14},{"id":"2503.07390","title":"PersonaBooth: Personalized Text-to-Motion Generation","created":"2025-03-10","cited_by_count":14},{"id":"2412.06702","title":"CHOICE: Coordinated Human-Object Interaction in Cluttered Environments for Pick-and-Place Actions","created":"2024-12-09","cited_by_count":12},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12},{"id":"2507.20220","title":"Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models","created":"2025-07-27","cited_by_count":11},{"id":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8},{"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},{"id":"2510.02566","title":"PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction","created":"2025-10-02","cited_by_count":7},{"id":"2605.06064","title":"PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers","created":"2026-05-07","cited_by_count":7},{"id":"2509.23635","title":"MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing","created":"2025-09-28","cited_by_count":5},{"id":"2512.24408","title":"DyStream: Streaming Dyadic Talking Heads Generation via Flow Matching-based Autoregressive Model","created":"2025-12-30","cited_by_count":5},{"id":"2511.13032","title":"Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts","created":"2025-11-17","cited_by_count":4},{"id":"2505.04203","title":"ELGAR: Expressive Cello Performance Motion Generation for Audio Rendition","created":"2025-05-07","cited_by_count":3},{"id":"2510.12573","title":"Learning Human Motion with Temporally Conditional Mamba","created":"2025-10-14","cited_by_count":2},{"id":"2411.04646","title":"DanceFusion: A Spatio-Temporal Skeleton Diffusion Transformer for Audio-Driven Dance Motion Reconstruction","created":"2024-11-07","cited_by_count":1},{"id":"2503.14040","title":"MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization","created":"2025-03-18","cited_by_count":1},{"id":"2511.14848","title":"Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video","created":"2025-11-18","cited_by_count":1}],"next_cursor":null}