{"list":"other","total":111,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"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":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"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":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2211.01095","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","created":"2022-11-02","cited_by_count":938},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"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":"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":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"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":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2310.14189","title":"Improved Techniques for Training Consistency Models","created":"2023-10-22","cited_by_count":439},{"id":"2309.06380","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","created":"2023-09-12","cited_by_count":395},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2305.08891","title":"Common Diffusion Noise Schedules and Sample Steps are Flawed","created":"2023-05-15","cited_by_count":310},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2410.11081","title":"Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models","created":"2024-10-14","cited_by_count":283},{"id":"2403.12015","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","created":"2024-03-18","cited_by_count":279},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"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":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245},{"id":"1807.00734","title":"The relativistic discriminator: a key element missing from standard GAN","created":"2018-07-02","cited_by_count":238},{"id":"2305.18455","title":"Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models","created":"2023-05-29","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":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"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":"2311.09257","title":"UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs","created":"2023-11-14","cited_by_count":166},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160},{"id":"2404.13686","title":"Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis","created":"2024-04-21","cited_by_count":156},{"id":"2410.05317","title":"Accelerating Diffusion Transformers with Token-wise Feature Caching","created":"2024-10-05","cited_by_count":156},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151},{"id":"2301.03396","title":"Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation","created":"2023-01-06","cited_by_count":142},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"2406.01733","title":"Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching","created":"2024-06-03","cited_by_count":142},{"id":"2305.18264","title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","created":"2023-05-29","cited_by_count":139},{"id":"2405.11473","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","created":"2024-05-19","cited_by_count":137},{"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":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128},{"id":"1705.09367","title":"Stabilizing Training of Generative Adversarial Networks through Regularization","created":"2017-05-25","cited_by_count":118},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"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":"2503.10592","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models","created":"2025-03-13","cited_by_count":98},{"id":"2405.07510","title":"PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator","created":"2024-05-13","cited_by_count":97},{"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":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80},{"id":"2405.05967","title":"Distilling Diffusion Models into Conditional GANs","created":"2024-05-09","cited_by_count":78},{"id":"2410.08151","title":"Progressive Autoregressive Video Diffusion Models","created":"2024-10-10","cited_by_count":68},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60},{"id":"2501.05441","title":"The GAN is dead; long live the GAN! A Modern GAN Baseline","created":"2025-01-09","cited_by_count":59},{"id":"2312.12491","title":"StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation","created":"2023-12-19","cited_by_count":58},{"id":"2506.05301","title":"SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training","created":"2025-06-05","cited_by_count":50},{"id":"2403.12706","title":"AnimateDiff-Lightning: Cross-Model Diffusion Distillation","created":"2024-03-19","cited_by_count":47},{"id":"2412.09856","title":"LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity","created":"2024-12-13","cited_by_count":43},{"id":"2402.00769","title":"AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data","created":"2024-02-01","cited_by_count":42},{"id":"2406.04324","title":"SF-V: Single Forward Video Generation Model","created":"2024-06-06","cited_by_count":40},{"id":"2405.05224","title":"Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation","created":"2024-05-08","cited_by_count":37}],"next_cursor":"100"}