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 209 篇，第 1 / 5 页

1. ICLR 2026$PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
2. ICLR 2026AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes
3. ICLR 2026Anchor Frame Bridging for Coherent First-Last Frame Video Generation
4. ICLR 2026Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models
5. ICLR 2026Astra: General Interactive World Model with Autoregressive Denoising
6. ICLR 2026Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model
7. ICLR 2026BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration
8. ICLR 2026BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
9. ICLR 2026BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
10. ICLR 2026CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
11. ICLR 2026ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Mask
12. ICLR 2026Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models
13. ICLR 2026Consistent Text-to-Image Generation via Scene De-Contextualization
14. ICLR 2026Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
15. ICLR 2026Controllable Video Generation with Provable Disentanglement
16. ICLR 2026DanceTogether: Generating Interactive Multi-Person Video without Identity Drifting
17. ICLR 2026Directional Textual Inversion for Personalized Text-to-Image Generation
18. ICLR 2026Diverse Text-to-Image Generation via Contrastive Noise Optimization
19. ICLR 2026DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
20. ICLR 2026DSA: Efficient Inference For Video Generation Models via Distributed Sparse Attention
21. ICLR 2026Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation
22. ICLR 2026Dynamic Reflections: Probing Video Representations with Text Alignment
23. ICLR 2026Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
24. ICLR 2026FastVMT: Eliminating Redundancy in Video Motion Transfer
25. ICLR 2026Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Model
26. ICLR 2026FreeViS: Training-free Video Stylization with Inconsistent References
27. ICLR 2026Generative View Stitching
28. ICLR 2026Geometry-aware 4D Video Generation for Robot Manipulation
29. ICLR 2026Group Critical-token Policy Optimization for Autoregressive Image Generation
30. ICLR 2026Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
31. ICLR 2026Gumbel Distillation for Parallel Text Generation
32. ICLR 2026Improving Autoregressive Video Modeling with History Understanding
33. ICLR 2026Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
34. ICLR 2026JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization
35. ICLR 2026Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
36. ICLR 2026Light-X: Generative 4D Video Rendering with Camera and Illumination Control
37. ICLR 2026LightCtrl: Training-free Controllable Video Relighting
38. ICLR 2026Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
39. ICLR 2026Logit‑KL Flow Matching: Non‑Autoregressive Text Generation via Sampling‑Hybrid Inference
40. ICLR 2026Long-Text-to-Image Generation via Compositional Prompt Decomposition
41. ICLR 2026LongLive: Real-time Interactive Long Video Generation
42. ICLR 2026Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective
43. ICLR 2026LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
44. ICLR 2026Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
45. ICLR 2026MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
46. ICLR 2026MATRIX: Mask Track Alignment for Interaction-aware Video Generation
47. ICLR 2026MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation
48. ICLR 2026MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
49. ICLR 2026MoCa: Modeling Object Consistency for 3D Camera Control in Video Generation
50. ICLR 2026Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

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。