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 1,185 篇，第 14 / 24 页

  1. ICLR 2025T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
  2. ICLR 2025TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
  3. ICLR 2025Temporal Reasoning Transfer from Text to Video
  4. ICLR 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
  5. ICLR 2025Trajectory attention for fine-grained video motion control
  6. ICLR 2025TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
  7. ICLR 2025VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
  8. ICLR 2025ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler
  9. ICLR 2025Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
  10. ICLR 2025VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing
  11. ICLR 2025VideoPhy: Evaluating Physical Commonsense for Video Generation
  12. ICLR 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
  13. ICLR 2025VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
  14. ICML 2025AdaWorld: Learning Adaptable World Models with Latent Actions
  15. ICML 2025Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners
  16. ICML 2025Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
  17. ICML 2025Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification
  18. ICML 2025Fast Video Generation with Sliding Tile Attention
  19. ICML 2025FlexiClip: Locality-Preserving Free-Form Character Animation
  20. ICML 2025GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
  21. ICML 2025How to Synthesize Text Data without Model Collapse?
  22. ICML 2025Imitation Learning from a Single Temporally Misaligned Video
  23. ICML 2025MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
  24. ICML 2025One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
  25. ICML 2025Reflection-Window Decoding: Text Generation with Selective Refinement
  26. ICML 2025Structure-Guided Large Language Models for Text-to-SQL Generation
  27. ICML 2025Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
  28. NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
  29. NeurIPS 2025Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
  30. NeurIPS 2025Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
  31. NeurIPS 2025Asymmetric Dual-Lens Video Deblurring
  32. NeurIPS 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
  33. NeurIPS 2025CSGO: Content-Style Composition in Text-to-Image Generation
  34. NeurIPS 2025Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation
  35. NeurIPS 2025DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
  36. NeurIPS 2025Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
  37. NeurIPS 2025Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
  38. NeurIPS 2025DisMo: Disentangled Motion Representations for Open-World Motion Transfer
  39. NeurIPS 2025DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
  40. NeurIPS 2025Don’t Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
  41. NeurIPS 2025Dynamic Shadow Unveils Invisible Semantics for Video Outpainting
  42. NeurIPS 2025EchoShot: Multi-Shot Portrait Video Generation
  43. NeurIPS 2025Emergent Temporal Correspondences from Video Diffusion Transformers
  44. NeurIPS 2025Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
  45. NeurIPS 2025Faster Video Diffusion with Trainable Sparse Attention
  46. NeurIPS 2025FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
  47. NeurIPS 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation
  48. NeurIPS 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
  49. NeurIPS 2025Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
  50. NeurIPS 2025From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos

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