{"list":"other","total":79,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"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":"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"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":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2101.12072","title":"Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting","created":"2021-01-28","cited_by_count":337},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","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":"2310.20700","title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","created":"2023-10-31","cited_by_count":233},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2412.02612","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","created":"2024-12-03","cited_by_count":224},{"id":"2406.08801","title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","created":"2024-06-13","cited_by_count":202},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163},{"id":"2206.08317","title":"Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition","created":"2022-06-16","cited_by_count":144},{"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":"2211.08553","title":"Hybrid Transformers for Music Source Separation","created":"2022-11-15","cited_by_count":134},{"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":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2409.02634","title":"Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency","created":"2024-09-04","cited_by_count":102},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83},{"id":"2212.00235","title":"VIDM: Video Implicit Diffusion Models","created":"2022-12-01","cited_by_count":78},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"id":"2508.10711","title":"NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale","created":"2025-08-14","cited_by_count":57},{"id":"2503.07418","title":"AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion","created":"2025-03-10","cited_by_count":55},{"id":"2507.03745","title":"StreamDiT: Real-Time Streaming Text-to-Video Generation","created":"2025-07-04","cited_by_count":48},{"id":"2311.15230","title":"GAIA: Zero-shot Talking Avatar Generation","created":"2023-11-26","cited_by_count":43},{"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":"2506.03099","title":"TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models","created":"2025-06-03","cited_by_count":26},{"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":"2410.03160","title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","created":"2024-10-04","cited_by_count":18},{"id":"2509.15130","title":"Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control","created":"2025-09-18","cited_by_count":18},{"id":"2408.02879","title":"Body of Her: A Preliminary Study on End-to-End Humanoid Agent","created":"2024-08-06","cited_by_count":15},{"id":"2307.02090","title":"Interactive Conversational Head Generation","created":"2023-07-05","cited_by_count":14},{"id":"2508.02944","title":"X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio","created":"2025-08-04","cited_by_count":3}],"next_cursor":null}