{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"1804.03786","title":"Nonlinear 3D Face Morphable Model","created":"2018-04-11","cited_by_count":157},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2104.04638","title":"Pixel Codec Avatars","created":"2021-04-09","cited_by_count":127},{"id":"2303.17480","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","created":"2023-03-29","cited_by_count":98},{"id":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92},{"id":"2305.05445","title":"StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator","created":"2023-05-09","cited_by_count":89},{"id":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86},{"id":"2406.02511","title":"V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation","created":"2024-06-04","cited_by_count":86},{"id":"2405.18991","title":"EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation","created":"2024-05-29","cited_by_count":77},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73},{"id":"2411.16331","title":"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation","created":"2024-11-25","cited_by_count":72},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70},{"id":"2405.07719","title":"USP: A Unified Sequence Parallelism Approach for Long Context Generative AI","created":"2024-05-13","cited_by_count":61},{"id":"2404.15264","title":"TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting","created":"2024-04-23","cited_by_count":60},{"id":"2401.04468","title":"MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation","created":"2024-01-09","cited_by_count":48},{"id":"2003.04852","title":"PANDA: A Gigapixel-level Human-centric Video Dataset","created":"2020-03-10","cited_by_count":45},{"id":"2402.05608","title":"Scalable Diffusion Models with State Space Backbone","created":"2024-02-08","cited_by_count":45},{"id":"2404.04478","title":"Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models","created":"2024-04-06","cited_by_count":41},{"id":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29},{"id":"2312.10921","title":"AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis","created":"2023-12-18","cited_by_count":16},{"id":"2404.12888","title":"Learn2Talk: 3D Talking Face Learns from 2D Talking Face","created":"2024-04-19","cited_by_count":16},{"id":"2501.01790","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","created":"2025-01-03","cited_by_count":13},{"id":"2404.19040","title":"GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splatting","created":"2024-04-29","cited_by_count":12},{"id":"2410.20974","title":"MovieCharacter: A Tuning-Free Framework for Controllable Character Video Synthesis","created":"2024-10-28","cited_by_count":12},{"id":"2309.00030","title":"Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis","created":"2023-08-31","cited_by_count":10},{"id":"2404.01543","title":"Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes","created":"2024-04-02","cited_by_count":8},{"id":"2407.05577","title":"Audio-driven High-resolution Seamless Talking Head Video Editing via StyleGAN","created":"2024-07-08","cited_by_count":6}],"next_cursor":null}