{"list":"other","total":111,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2511.22699","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","created":"2025-11-27","cited_by_count":277},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2402.13929","title":"SDXL-Lightning: Progressive Adversarial Diffusion Distillation","created":"2024-02-21","cited_by_count":266},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2509.25161","title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","created":"2025-09-29","cited_by_count":234},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217},{"id":"2311.05556","title":"LCM-LoRA: A Universal Stable-Diffusion Acceleration Module","created":"2023-11-09","cited_by_count":211},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2412.14169","title":"Autoregressive Video Generation without Vector Quantization","created":"2024-12-18","cited_by_count":186},{"id":"2602.02214","title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","created":"2026-02-02","cited_by_count":184},{"id":"2310.15169","title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","created":"2023-10-23","cited_by_count":180},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170},{"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":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","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":"2405.11473","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","created":"2024-05-19","cited_by_count":137},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131},{"id":"2410.10989","title":"Liger Kernel: Efficient Triton Kernels for LLM Training","created":"2024-10-14","cited_by_count":130},{"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":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104},{"id":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98},{"id":"2504.08388","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","created":"2025-04-11","cited_by_count":97},{"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":"2509.24695","title":"SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer","created":"2025-09-29","cited_by_count":94},{"id":"2510.08431","title":"Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency","created":"2025-10-09","cited_by_count":86},{"id":"2512.04678","title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","created":"2025-12-04","cited_by_count":86},{"id":"2510.22200","title":"LongCat-Video Technical Report","created":"2025-10-25","cited_by_count":85},{"id":"2512.22096","title":"Yume-1.5: A Text-Controlled Interactive World Generation Model","created":"2025-12-26","cited_by_count":84},{"id":"2507.17744","title":"Yume: An Interactive World Generation Model","created":"2025-07-23","cited_by_count":81},{"id":"2510.16888","title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback","created":"2025-10-19","cited_by_count":79},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73},{"id":"2510.09212","title":"Stable Video Infinity: Infinite-Length Video Generation with Error Recycling","created":"2025-10-10","cited_by_count":73},{"id":"2503.07418","title":"AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion","created":"2025-03-10","cited_by_count":55},{"id":"2503.18886","title":"CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models","created":"2025-03-24","cited_by_count":52},{"id":"2512.15702","title":"End-to-End Training for Autoregressive Video Diffusion via Self-Resampling","created":"2025-12-17","cited_by_count":52},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48},{"id":"2511.04675","title":"InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation","created":"2025-11-06","cited_by_count":45},{"id":"2511.22677","title":"Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield","created":"2025-11-27","cited_by_count":45},{"id":"2506.09045","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","created":"2025-06-10","cited_by_count":41},{"id":"2512.08931","title":"Astra: General Interactive World Model with Autoregressive Denoising","created":"2025-12-09","cited_by_count":33},{"id":"2512.16093","title":"TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times","created":"2025-12-18","cited_by_count":33},{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33},{"id":"2210.04955","title":"f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation","created":"2022-10-10","cited_by_count":32},{"id":"2601.16914","title":"LoL: Longer than Longer, Scaling Video Generation to Hour","created":"2026-01-23","cited_by_count":32},{"id":"2511.07399","title":"StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation","created":"2025-11-10","cited_by_count":30},{"id":"2503.14151","title":"Concat-ID: Towards Universal Identity-Preserving Video Synthesis","created":"2025-03-18","cited_by_count":28},{"id":"2508.07901","title":"Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation","created":"2025-08-11","cited_by_count":28},{"id":"2503.18940","title":"Training-free Diffusion Acceleration with Bottleneck Sampling","created":"2025-03-24","cited_by_count":25}],"next_cursor":"100"}