{"list":"other","total":60,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"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":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"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":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"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":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"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":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151},{"id":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149},{"id":"2301.03396","title":"Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation","created":"2023-01-06","cited_by_count":142},{"id":"2301.03786","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","created":"2023-01-10","cited_by_count":136},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"2401.00374","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","created":"2023-12-31","cited_by_count":105},{"id":"2310.06313","title":"Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models","created":"2023-10-10","cited_by_count":104},{"id":"2407.12705","title":"IMAGDressing-v1: Customizable Virtual Dressing","created":"2024-07-17","cited_by_count":100},{"id":"2410.07718","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","created":"2024-10-10","cited_by_count":97},{"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":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2406.02511","title":"V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation","created":"2024-06-04","cited_by_count":86},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","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":"2411.16331","title":"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation","created":"2024-11-25","cited_by_count":72},{"id":"2404.19110","title":"EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars","created":"2024-04-29","cited_by_count":66},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56},{"id":"2502.09533","title":"Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model","created":"2025-02-13","cited_by_count":49},{"id":"2210.06465","title":"AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars","created":"2022-10-12","cited_by_count":46},{"id":"2412.04448","title":"MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation","created":"2024-12-05","cited_by_count":38},{"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":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29},{"id":"2301.04474","title":"Speech Driven Video Editing via an Audio-Conditioned Diffusion Model","created":"2023-01-10","cited_by_count":28},{"id":"2403.06363","title":"Say Anything with Any Style","created":"2024-03-11","cited_by_count":26},{"id":"2506.10941","title":"VINCIE: Unlocking In-context Image Editing from Video","created":"2025-06-12","cited_by_count":17},{"id":"2405.15758","title":"InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation","created":"2024-05-24","cited_by_count":16},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15},{"id":"2512.22905","title":"JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation","created":"2025-12-28","cited_by_count":15},{"id":"2504.18087","title":"Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation","created":"2025-04-25","cited_by_count":11},{"id":"2503.15851","title":"Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion","created":"2025-03-20","cited_by_count":9},{"id":"2410.13726","title":"DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation","created":"2024-10-17","cited_by_count":8},{"id":"2502.07203","title":"Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion","created":"2025-02-11","cited_by_count":8},{"id":"1904.01509","title":"FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation","created":"2019-04-02","cited_by_count":7},{"id":"2111.02751","title":"FEAFA+: An Extended Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation","created":"2021-11-04","cited_by_count":7},{"id":"2412.07754","title":"PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation","created":"2024-12-10","cited_by_count":5},{"id":"2410.14283","title":"Takin-ADA: Emotion Controllable Audio-Driven Animation with Canonical and Landmark Loss Optimization","created":"2024-10-18","cited_by_count":4},{"id":"2510.07940","title":"TTOM: Test-Time Optimization and Memorization for Compositional Video Generation","created":"2025-10-09","cited_by_count":4},{"id":"2601.08011","title":"TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models","created":"2026-01-12","cited_by_count":4},{"id":"2412.04000","title":"IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head Generation","created":"2024-12-05","cited_by_count":3}],"next_cursor":null}