{"list":"other","total":52,"rows":[{"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":"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"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":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"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":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"1807.00734","title":"The relativistic discriminator: a key element missing from standard GAN","created":"2018-07-02","cited_by_count":238},{"id":"2404.04057","title":"Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation","created":"2024-04-05","cited_by_count":214},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151},{"id":"2301.13430","title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis","created":"2023-01-31","cited_by_count":131},{"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":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"2107.06592","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","created":"2021-07-14","cited_by_count":113},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2411.10061","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","created":"2024-11-15","cited_by_count":72},{"id":"2411.16331","title":"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation","created":"2024-11-25","cited_by_count":72},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67},{"id":"2404.15264","title":"TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting","created":"2024-04-23","cited_by_count":60},{"id":"2501.05441","title":"The GAN is dead; long live the GAN! A Modern GAN Baseline","created":"2025-01-09","cited_by_count":59},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40},{"id":"2403.09069","title":"Dyadic Interaction Modeling for Social Behavior Generation","created":"2024-03-14","cited_by_count":32},{"id":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30},{"id":"2507.03905","title":"EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation","created":"2025-07-05","cited_by_count":29},{"id":"2403.00274","title":"CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation","created":"2024-03-01","cited_by_count":22},{"id":"2508.19320","title":"MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation","created":"2025-08-26","cited_by_count":19},{"id":"2509.21574","title":"X-Streamer: Unified Human World Modeling with Audiovisual Interaction","created":"2025-09-25","cited_by_count":18},{"id":"2507.00472","title":"ARIG: Autoregressive Interactive Head Generation for Real-time Conversations","created":"2025-07-01","cited_by_count":16},{"id":"2506.14742","title":"SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting","created":"2025-06-17","cited_by_count":9},{"id":"2303.14044","title":"MusicFace: Music-driven Expressive Singing Face Synthesis","created":"2023-03-24","cited_by_count":5},{"id":"2505.20861","title":"Exploring Timeline Control for Facial Motion Generation","created":"2025-05-27","cited_by_count":4},{"id":"2503.12052","title":"A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments","created":"2025-03-15","cited_by_count":2}],"next_cursor":null}