{"list":"other","total":71,"rows":[{"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"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":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"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":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2101.09258","title":"Maximum Likelihood Training of Score-Based Diffusion Models","created":"2021-01-22","cited_by_count":672},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2503.09573","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","created":"2025-03-12","cited_by_count":409},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"2403.12015","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","created":"2024-03-18","cited_by_count":279},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2012.09855","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","created":"2020-12-17","cited_by_count":243},{"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":"1610.09038","title":"Professor Forcing: A New Algorithm for Training Recurrent Networks","created":"2016-10-27","cited_by_count":216},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"1910.00292","title":"Generalization in Generation: A closer look at Exposure Bias","created":"2019-10-01","cited_by_count":123},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123},{"id":"2305.09515","title":"AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation","created":"2023-05-16","cited_by_count":118},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104},{"id":"2308.15321","title":"Elucidating the Exposure Bias in Diffusion Models","created":"2023-08-29","cited_by_count":101},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99},{"id":"2207.11148","title":"InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images","created":"2022-07-22","cited_by_count":82},{"id":"2410.16794","title":"One-Step Diffusion Distillation through Score Implicit Matching","created":"2024-10-22","cited_by_count":71},{"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":"2410.14919","title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","created":"2024-10-19","cited_by_count":47},{"id":"2412.07720","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","created":"2024-12-10","cited_by_count":45},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34},{"id":"2412.12095","title":"Causal Diffusion Transformers for Generative Modeling","created":"2024-12-16","cited_by_count":31},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30},{"id":"2410.19310","title":"Flow Generator Matching","created":"2024-10-25","cited_by_count":26},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26},{"id":"1906.04612","title":"On Stabilizing Generative Adversarial Training with Noise","created":"2019-06-11","cited_by_count":25},{"id":"2411.00083","title":"Learning Visual Parkour from Generated Images","created":"2024-10-31","cited_by_count":18},{"id":"2504.20996","title":"X-Fusion: Introducing New Modality to Frozen Large Language Models","created":"2025-04-29","cited_by_count":13},{"id":"2310.03256","title":"Toward One-Second Latency: Evolution of Live Media Streaming","created":"2023-10-05","cited_by_count":3}],"next_cursor":null}