文生视频论文趋势 2023–2026

视频生成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,185 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

文生视频论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202352211780170
2024553517140247
2025915914156320
20261019455198448

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

全部文生视频论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 299 篇，第 4 / 6 页

  1. NeurIPS 2025PlayerOne: Egocentric World Simulator
  2. NeurIPS 2025Policy Optimized Text-to-Image Pipeline Design
  3. NeurIPS 2025PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
  4. NeurIPS 2025Precise Information Control in Long-Form Text Generation
  5. NeurIPS 2025Preventing Shortcuts in Adapter Training via Providing the Shortcuts
  6. NeurIPS 2025Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation
  7. NeurIPS 2025Rare Text Semantics Were Always There in Your Diffusion Transformer
  8. NeurIPS 2025Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
  9. NeurIPS 2025REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
  10. NeurIPS 2025Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
  11. NeurIPS 2025ROSE: Remove Objects with Side Effects in Videos
  12. NeurIPS 2025Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
  13. NeurIPS 2025Sekai: A Video Dataset towards World Exploration
  14. NeurIPS 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
  15. NeurIPS 2025SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
  16. NeurIPS 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
  17. NeurIPS 2025Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
  18. NeurIPS 2025Storyboard-guided Alignment for Fine-grained Video Action Recognition
  19. NeurIPS 2025StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
  20. NeurIPS 2025T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
  21. NeurIPS 2025Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models
  22. NeurIPS 2025The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
  23. NeurIPS 2025Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
  24. NeurIPS 2025Training-Free Efficient Video Generation via Dynamic Token Carving
  25. NeurIPS 2025Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
  26. NeurIPS 2025UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
  27. NeurIPS 2025UniTransfer: Video Concept Transfer via Progressive Spatio-Temporal Decomposition
  28. NeurIPS 2025Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
  29. NeurIPS 2025VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness
  30. NeurIPS 2025VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
  31. NeurIPS 2025VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
  32. NeurIPS 2025Video World Models with Long-term Spatial Memory
  33. NeurIPS 2025VideoMAR: Autoregressive Video Generation with Continuous Tokens
  34. NeurIPS 2025VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
  35. NeurIPS 2025VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
  36. NeurIPS 2025ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models
  37. NeurIPS 2025VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models
  38. NeurIPS 2025VORTA: Efficient Video Diffusion via Routing Sparse Attention
  39. NeurIPS 2025Whole-Body Conditioned Egocentric Video Prediction
  40. NeurIPS 2025WISA: World simulator assistant for physics-aware text-to-video generation
  41. NeurIPS 2025WorldModelBench: Judging Video Generation Models As World Models
  42. NeurIPS 2025WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
  43. NeurIPS 2024AID: Attention Interpolation of Text-to-Image Diffusion
  44. NeurIPS 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
  45. NeurIPS 2024AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
  46. NeurIPS 2024Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
  47. NeurIPS 2024AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
  48. NeurIPS 2024Beyond Aesthetics: Cultural Competence in Text-to-Image Models
  49. NeurIPS 2024Boosting Text-to-Video Generative Model with MLLMs Feedback
  50. NeurIPS 2024ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查文生视频在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "text-to-video"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「多模态生成」下的其他主题