mlsanityData to 14 Oct 2026

LongCat-Video Technical Report

arXiv 2510.22200 ↗First posted 25 Oct 2025cs.CVcited by 85

On the map: World models → Video-generation world models and simulators

Abstract (arXiv)

Video generation is a critical pathway toward world models, with efficient long video inference as a key capability. Toward this end, we introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across multiple video generation tasks. It particularly excels in efficient and high-quality long video generation, representing our first step toward world models. Key features include: Unified architecture for multiple tasks: Built on the Diffusion Transformer (DiT) framework, LongCat-Video supports Text-to-Video, Image-to-Video, and Video-Continuation tasks with a single model; Long video generation: Pretraining on Video-Continuation tasks enables LongCat-Video to maintain high quality and temporal coherence in the generation of minutes-long videos; Efficient inference: LongCat-Video generates 720p, 30fps videos within minutes by employing a coarse-to-fine generation strategy along both the temporal and spatial axes. Block Sparse Attention further enhances efficiency, particularly at high resolutions; Strong performance with multi-reward RLHF: Multi-reward RLHF training enables LongCat-Video to achieve performance on par with the latest closed-source and leading open-source models. Code and model weights are publicly available to accelerate progress in the field.

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). Placed in Video-generation world models and simulators, one of 11 directions in World models. Builds on 38 of its 42 references that are in the map. First posted on arXiv 25 Oct 2025.

Builds on

38 of 42 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness27 Mar
  2. 2025Wan: Open and Advanced Large-Scale Video Generative Models26 Mar
  3. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  4. 2022Scalable Diffusion Models with Transformers19 Dec
  5. 2022Flow Matching for Generative Modeling6 Oct
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov

Other references · 32

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  6. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  7. 2020GLU Variants Improve Transformercited by 1,804
  8. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  9. 2019Root Mean Square Layer Normalizationcited by 1,480
  10. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  11. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  12. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
20 more
  1. 2024LLaVA-Video: Video Instruction Tuning With Synthetic Datacited by 583
  2. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 519
  3. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  4. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 413
  5. 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attentioncited by 407
  6. 2025Improving Video Generation with Human Feedbackcited by 284
  7. 2020Query-Key Normalization for Transformerscited by 280
  8. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 211
  9. 2025MoBA: Mixture of Block Attention for Long-Context LLMscited by 198
  10. 2024T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generationcited by 185
  11. 2025MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDEcited by 178
  12. 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 171
  13. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  14. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 156
  15. 2023UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretrainingcited by 151
  16. 2025VSA: Faster Video Diffusion with Trainable Sparse Attentioncited by 104
  17. 2024Phased Consistency Modelscited by 85
  18. 2025Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understandingcited by 81
  19. 2025CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Modelscited by 52
  20. 2025Fine-Grained GRPO for Precise Preference Alignment in Flow Modelscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 78.

85 papers.

Sort:

By area:

  1. 2026Advancing Open-source World Modelscited by 154
  2. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  3. 2026MOVA: Towards Scalable and Synchronized Video-Audio Generationcited by 43
  4. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  5. 2026WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluationcited by 39
  6. 2026LoL: Longer than Longer, Scaling Video Generation to Hourcited by 32
  7. 2026LLM-as-a-Verifier: A General-Purpose Verification Frameworkcited by 30
  8. 2026Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantizationcited by 23
  9. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 15
  10. 2026Manifold-Aware Exploration for Reinforcement Learning in Video Generationcited by 15
  11. 2026Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Modelscited by 15
  12. 2026Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligencecited by 15
38 more
  1. 2026OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generatorscited by 14
  2. 2026StableWorld: Towards Stable and Consistent Long Interactive Video Generationcited by 12
  3. 2026LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AVcited by 9
  4. 2026Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planningcited by 8
  5. 2025LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generationcited by 7
  6. 2026TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generationcited by 7
  7. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 7
  8. 2026PhyWorld: Physics-Faithful World Model for Video Generationcited by 6
  9. 2026LongCat-Video-Avatar 1.5 Technical Reportcited by 6
  10. 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillationcited by 6
  11. 2026WorldOlympiad: Can Your World Model Survive a Triathlon?cited by 6
  12. 2025YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidancecited by 5
  13. 2025DreaMontage: Arbitrary Frame-Guided One-Shot Video Generationcited by 5
  14. 2026OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyondcited by 5
  15. 2026Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusioncited by 5
  16. 2025SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Modelscited by 4
  17. 2026WildActor: Unconstrained Identity-Preserving Video Generationcited by 4
  18. 2026HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulationcited by 4
  19. 2026Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimizationcited by 4
  20. 2026Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matchingcited by 4
  21. 2026H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Modelscited by 4
  22. 2025YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biasescited by 3
  23. 2026EverAnimate: Minute-Scale Human Animation via Latent Flow Restorationcited by 3
  24. 2026Geo-Align: Video Generation Alignment via Metric Geometry Rewardcited by 3
  25. 2026Light Interaction: Training-Free Inference Acceleration for Interactive Video World Modelscited by 3
  26. 2026Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutionscited by 3
  27. 2026Budget-Constrained Step-Level Diffusion Cachingcited by 3
  28. 2026Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioningcited by 3
  29. 2026RECAP-Forcing: Retaining Content Appearances for Long Video Generationcited by 3
  30. 2026Astronex-World 1.0: Real-Time Interactive World Model Foundationcited by 3
  31. 2026Advances in GRPO for Generation Models: A Surveycited by 2
  32. 2026Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generationcited by 2
  33. 2026Steering Video Diffusion Transformers with Massive Activationscited by 2
  34. 2026Audio-Visual Intelligence in Large Foundation Modelscited by 2
  35. 2026Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modelingcited by 2
  36. 2026Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observationscited by 2
  37. 2026AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPOcited by 2
  38. 2026MoWorld: A Flash World Modelcited by 2

50 most cited of 85 All 85 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Owl-1: Omni World Model for Consistent Long Video Generation
  2. 2025LongLive: Real-time Interactive Long Video Generation
  3. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
  4. 2026LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
  5. 2024FlexiFilm: Long Video Generation with Flexible Conditions
  6. 2026Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model
  7. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation
  8. 2025LongVie 2: Multimodal Controllable Ultra-Long Video World Model