{"list":"other","total":73,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"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":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"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":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2406.08801","title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","created":"2024-06-13","cited_by_count":202},{"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":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168},{"id":"2405.04233","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","created":"2024-05-07","cited_by_count":160},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160},{"id":"2509.23951","title":"HunyuanImage 3.0 Technical Report","created":"2025-09-28","cited_by_count":149},{"id":"2412.00733","title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","created":"2024-12-01","cited_by_count":122},{"id":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120},{"id":"2411.10958","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","created":"2024-11-17","cited_by_count":114},{"id":"2505.13389","title":"VSA: Faster Video Diffusion with Trainable Sparse Attention","created":"2025-05-19","cited_by_count":104},{"id":"2410.07718","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","created":"2024-10-10","cited_by_count":97},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87},{"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":"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":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2502.04896","title":"Goku: Flow Based Video Generative Foundation Models","created":"2025-02-07","cited_by_count":67},{"id":"2505.11594","title":"SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training","created":"2025-05-16","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":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61},{"id":"2506.13691","title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","created":"2025-06-16","cited_by_count":57},{"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":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44},{"id":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","cited_by_count":41},{"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":"2412.19238","title":"FineVQ: Fine-Grained User Generated Content Video Quality Assessment","created":"2024-12-26","cited_by_count":28},{"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":"2506.04648","title":"FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion","created":"2025-06-05","cited_by_count":19},{"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":"2502.13995","title":"FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation","created":"2025-02-19","cited_by_count":18},{"id":"2510.18775","title":"UltraGen: High-Resolution Video Generation with Hierarchical Attention","created":"2025-10-21","cited_by_count":18},{"id":"2507.12956","title":"FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers","created":"2025-07-17","cited_by_count":13},{"id":"2508.20210","title":"InfinityHuman: Towards Long-Term Audio-Driven Human","created":"2025-08-27","cited_by_count":9},{"id":"2506.11144","title":"AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation","created":"2025-06-11","cited_by_count":8},{"id":"2510.12089","title":"Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback","created":"2025-10-14","cited_by_count":8},{"id":"2510.23581","title":"Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation","created":"2025-10-27","cited_by_count":4},{"id":"2509.19965","title":"SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding","created":"2025-09-24","cited_by_count":2},{"id":"2510.06612","title":"A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages","created":"2025-10-08","cited_by_count":2},{"id":"2510.22810","title":"MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control","created":"2025-10-26","cited_by_count":2},{"id":"2510.08587","title":"EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation","created":"2025-10-03","cited_by_count":1},{"id":"2510.10269","title":"VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework","created":"2025-10-11","cited_by_count":1}],"next_cursor":null}