{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"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":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2201.02610","title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","created":"2022-01-07","cited_by_count":181},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88},{"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":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67},{"id":"2309.17261","title":"Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors","created":"2023-09-29","cited_by_count":64},{"id":"2403.10518","title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","created":"2024-03-15","cited_by_count":61},{"id":"1711.05376","title":"Sliced Wasserstein Distance for Learning Gaussian Mixture Models","created":"2017-11-15","cited_by_count":59},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46},{"id":"2311.01015","title":"Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs","created":"2023-11-02","cited_by_count":45},{"id":"2405.18525","title":"REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment","created":"2024-05-28","cited_by_count":45},{"id":"2306.09532","title":"Hierarchical Planning and Control for Box Loco-Manipulation","created":"2023-06-15","cited_by_count":44},{"id":"2305.11094","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","created":"2023-05-18","cited_by_count":40},{"id":"2309.09294","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","created":"2023-09-17","cited_by_count":40},{"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":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35},{"id":"2304.04150","title":"RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning","created":"2023-04-09","cited_by_count":30},{"id":"2205.14313","title":"Learning to Use Chopsticks in Diverse Gripping Styles","created":"2022-05-28","cited_by_count":29},{"id":"2403.17422","title":"InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion","created":"2024-03-26","cited_by_count":28},{"id":"2412.16982","title":"InterDance:Reactive 3D Dance Generation with Realistic Duet Interactions","created":"2024-12-22","cited_by_count":22},{"id":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21},{"id":"2312.15900","title":"Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control","created":"2023-12-26","cited_by_count":18},{"id":"2106.02040","title":"Towards Learning to Play Piano with Dexterous Hands and Touch","created":"2021-06-03","cited_by_count":17},{"id":"2503.19383","title":"MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animation","created":"2025-03-25","cited_by_count":14},{"id":"2504.00430","title":"Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion","created":"2025-04-01","cited_by_count":12},{"id":"2305.04654","title":"Synthesize Dexterous Nonprehensile Pregrasp for Ungraspable Objects","created":"2023-05-08","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":"2408.16506","title":"Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation","created":"2024-08-29","cited_by_count":10},{"id":"2410.05791","title":"F\\\"urElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance","created":"2024-10-08","cited_by_count":10},{"id":"2411.18654","title":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward","created":"2024-11-27","cited_by_count":7},{"id":"2406.09326","title":"PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance","created":"2024-06-13","cited_by_count":5},{"id":"2502.16913","title":"HVIS: A Human-like Vision and Inference System for Human Motion Prediction","created":"2025-02-24","cited_by_count":3}],"next_cursor":null}