{"list":"other","total":52,"rows":[{"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":"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":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"2509.25161","title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","created":"2025-09-29","cited_by_count":234},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"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":"2305.05445","title":"StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator","created":"2023-05-09","cited_by_count":89},{"id":"2510.22200","title":"LongCat-Video Technical Report","created":"2025-10-25","cited_by_count":85},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80},{"id":"2411.10061","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","created":"2024-11-15","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":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61},{"id":"2501.08453","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","created":"2025-01-14","cited_by_count":60},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43},{"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":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","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":"2508.19209","title":"OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation","created":"2025-08-26","cited_by_count":32},{"id":"2203.07931","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","created":"2022-03-15","cited_by_count":30},{"id":"2505.21448","title":"OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers","created":"2025-05-27","cited_by_count":27},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20},{"id":"2511.23475","title":"AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement","created":"2025-11-28","cited_by_count":20},{"id":"2601.00664","title":"Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation","created":"2026-01-02","cited_by_count":19},{"id":"2408.03284","title":"ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer","created":"2024-08-06","cited_by_count":16},{"id":"2512.13313","title":"KlingAvatar 2.0 Technical Report","created":"2025-12-15","cited_by_count":13},{"id":"2601.10103","title":"FlowAct-R1: Towards Interactive Humanoid Video Generation","created":"2026-01-15","cited_by_count":11},{"id":"2503.19824","title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers","created":"2025-03-25","cited_by_count":10},{"id":"2504.04010","title":"DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion","created":"2025-04-05","cited_by_count":10},{"id":"2005.05514","title":"TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model","created":"2020-05-12","cited_by_count":9},{"id":"2508.20210","title":"InfinityHuman: Towards Long-Term Audio-Driven Human","created":"2025-08-27","cited_by_count":9},{"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":"2506.19833","title":"Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router","created":"2025-06-24","cited_by_count":6},{"id":"2512.13495","title":"Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation","created":"2025-12-15","cited_by_count":3},{"id":"2508.03050","title":"Multi-human Interactive Talking Dataset","created":"2025-08-05","cited_by_count":2}],"next_cursor":null}