文生视频论文趋势 2023–2026

主要结论

• 文生视频论文从 2023 年的 170 篇增长到 2026 年的 448 篇，三年间扩大到约 2.6 倍。
• CVPR 是发文生视频论文最多的会议，2023–2026 年共 574 篇，占四个会议总量的 48%。
• 交叉方向里涨得最快的是深度学习 · generative models and autoencoders：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 26 篇。
• 在「多模态生成」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的叙事生成是 15 倍，文生视频是 2.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
• ICML 2026DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
• ICLR 2026$PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
• CVPR 20263D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
• NeurIPS 2025Dynamic Shadow Unveils Invisible Semantics for Video Outpainting
• ICML 2025GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
• ICLR 20253DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
• CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
• NeurIPS 2024ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
• ICML 2024Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
• ICLR 2024Provable Robust Watermarking for AI-Generated Text
• CVPR 2024Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning
• NeurIPS 2023Any-to-Any Generation via Composable Diffusion
• ICML 2023Controlled Text Generation with Natural Language Instructions
• ICLR 2023CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
• CVPR 20231000 FPS HDR Video With a Spike-RGB Hybrid Camera
• NeurIPS 2026Character Mixing for Video Generation
• ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
• ICLR 2026Anchor Frame Bridging for Coherent First-Last Frame Video Generation
• CVPR 2026Building a Precise Video Language with Human-AI Oversight

全部文生视频论文

共 59 篇，第 1 / 2 页

1. ICLR 20253DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
2. ICLR 20254K4DGen: Panoramic 4D Generation at 4K Resolution
3. ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
4. ICLR 2025Animate-X: Universal Character Image Animation with Enhanced Motion Representation
5. ICLR 2025ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation
6. ICLR 2025Autoregressive Video Generation without Vector Quantization
7. ICLR 2025Bayesian WeakS-to-Strong from Text Classification to Generation
8. ICLR 2025Beyond FVD: An Enhanced Evaluation Metrics for Video Generation Distribution Quality
9. ICLR 2025Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach
10. ICLR 2025Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation
11. ICLR 2025CameraCtrl: Enabling Camera Control for Video Diffusion Models
12. ICLR 2025CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
13. ICLR 2025Consistent Flow Distillation for Text-to-3D Generation
14. ICLR 2025DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation
15. ICLR 2025Denoising Autoregressive Transformers for Scalable Text-to-Image Generation
16. ICLR 2025Energy-Based Diffusion Language Models for Text Generation
17. ICLR 2025Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
18. ICLR 2025Erasing Concept Combination from Text-to-Image Diffusion Model
19. ICLR 2025Forking Paths in Neural Text Generation
20. ICLR 2025FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
21. ICLR 2025GameGen-X: Interactive Open-world Game Video Generation
22. ICLR 2025GenEx: Generating an Explorable World
23. ICLR 2025GLOMA: Global Video Text Spotting with Morphological Association
24. ICLR 2025Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models
25. ICLR 2025Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
26. ICLR 2025I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
27. ICLR 2025Infinite-Resolution Integral Noise Warping for Diffusion Models
28. ICLR 2025IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
29. ICLR 2025MMTEB: Massive Multilingual Text Embedding Benchmark
30. ICLR 2025MotionClone: Training-Free Motion Cloning for Controllable Video Generation
31. ICLR 2025NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative
32. ICLR 2025OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation
33. ICLR 2025OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
34. ICLR 2025Precise Parameter Localization for Textual Generation in Diffusion Models
35. ICLR 2025Progressive Compositionality in Text-to-Image Generative Models
36. ICLR 2025PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-Task
37. ICLR 2025Pyramidal Flow Matching for Efficient Video Generative Modeling
38. ICLR 2025Real-Time Video Generation with Pyramid Attention Broadcast
39. ICLR 2025RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation
40. ICLR 2025SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
41. ICLR 2025SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation
42. ICLR 2025SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
43. ICLR 2025SMITE: Segment Me In TimE
44. ICLR 2025Solving New Tasks by Adapting Internet Video Knowledge
45. ICLR 2025SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix
46. ICLR 2025SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
47. ICLR 2025T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
48. ICLR 2025TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
49. ICLR 2025Temporal Reasoning Transfer from Text to Video
50. ICLR 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias

常见问题

2023–2026 年四大会议一共有多少篇文生视频论文？

共 1,185 篇，按年份分别是 2023 年 170 篇、2024 年 247 篇、2025 年 320 篇、2026 年 448 篇。

NeurIPS 2026 有多少篇文生视频论文？

NeurIPS 2026 有 101 篇文生视频论文，上一届是 91 篇。

ICLR 2026 有多少篇文生视频论文？

ICLR 2026 有 94 篇文生视频论文，上一届是 59 篇。

ICML 2026 有多少篇文生视频论文？

ICML 2026 有 55 篇文生视频论文，上一届是 14 篇。

CVPR 2026 有多少篇文生视频论文？

CVPR 2026 有 198 篇文生视频论文，上一届是 156 篇。

哪个会议的文生视频论文最多？

CVPR，2023–2026 年共 574 篇。