{"list":"other","total":73,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"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":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"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":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","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":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"2406.08801","title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","created":"2024-06-13","cited_by_count":202},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"1710.00421","title":"Video Generation From Text","created":"2017-10-01","cited_by_count":154},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143},{"id":"2301.03396","title":"Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation","created":"2023-01-06","cited_by_count":142},{"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":"1910.09139","title":"DwNet: Dense warp-based network for pose-guided human video generation","created":"2019-10-21","cited_by_count":115},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2409.02634","title":"Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency","created":"2024-09-04","cited_by_count":102},{"id":"2406.02511","title":"V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation","created":"2024-06-04","cited_by_count":86},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"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":"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":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2407.17438","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","created":"2024-07-24","cited_by_count":64},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44},{"id":"2311.15230","title":"GAIA: Zero-shot Talking Avatar Generation","created":"2023-11-26","cited_by_count":43},{"id":"2409.01876","title":"CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention","created":"2024-09-03","cited_by_count":39},{"id":"2501.10687","title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","created":"2025-01-18","cited_by_count":33},{"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":"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":"2509.09595","title":"Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis","created":"2025-09-11","cited_by_count":21},{"id":"2409.07649","title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","created":"2024-09-11","cited_by_count":20},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20},{"id":"2504.04126","title":"Multi-identity Human Image Animation with Structural Video Diffusion","created":"2025-04-05","cited_by_count":13},{"id":"2410.07151","title":"DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation","created":"2024-09-23","cited_by_count":9},{"id":"2510.07249","title":"TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation","created":"2025-10-08","cited_by_count":6}],"next_cursor":null}