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 3 / 24 页

  1. CVPR 2026MovieRecapsQA A Multimodal Open-Ended Video Question-Answering Benchmark
  2. CVPR 2026Multi-level Causal LLM-based Text-to-Motion Generation with Human Alignment
  3. CVPR 2026MultiBanana A Challenging Benchmark for Multi-Reference Text-to-Image Generation
  4. CVPR 2026MultiShotMaster A Controllable Multi-Shot Video Generation Framework
  5. CVPR 2026Next-Scale Autoregressive Models for Text-to-Motion Generation
  6. CVPR 2026Omni2Sound Towards Unified Video-Text-to-Audio Generation
  7. CVPR 2026OneStory Coherent Multi-Shot Video Generation with Adaptive Memory
  8. CVPR 2026ORBIT Benchmarking SfM in the Wild with 360deg Video
  9. CVPR 2026ORV 4D Occupancy-centric Robot Video Generation
  10. CVPR 2026OSPO Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation
  11. CVPR 2026PAM A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation
  12. CVPR 2026Pantheon360 Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion
  13. CVPR 2026ParTY Part-Guidance for Expressive Text-to-Motion Synthesis
  14. CVPR 2026Physical Simulator In-the-Loop Video Generation
  15. CVPR 2026PhysVid Physics Aware Local Conditioning for Generative Video Models
  16. CVPR 2026Plenoptic Video Generation
  17. CVPR 2026PoseAnything General Pose-guided Video Generation with Part-aware Temporal Coherence
  18. CVPR 2026Property-Informed Diffusion-Based Text-to-Microstructure Generation
  19. CVPR 2026PS-SR Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
  20. CVPR 2026PyraTok Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
  21. CVPR 2026Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep
  22. CVPR 2026Reasoning Diffusion for Unpaired Test Time Out-of-distribution Text-Image to Video
  23. CVPR 2026RecEdit-Drive 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes
  24. CVPR 2026Reconstruction-Guided Slot Curriculum Addressing Object Over-Fragmentation in Video Object-Centric Learning
  25. CVPR 2026ReDirector Creating Any-Length Video Retakes with Rotary Camera Encoding
  26. CVPR 2026Ref4D-VideoBench Four-Dimensional Reference-Based Evaluation of Text-to-Video Generative Models
  27. CVPR 2026Relightful Video Portrait Harmonization
  28. CVPR 2026Residual Decoder Adapter ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
  29. CVPR 2026Resolving the Identity Crisis in Text-to-Image Generation
  30. CVPR 2026Restore Text First Enhance Image Later Two-Stage Scene Text Image
  31. CVPR 2026Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
  32. CVPR 2026Reward Forcing Efficient Streaming Video Generation with Rewarded Distribution Matching
  33. CVPR 2026RFDM Residual Flow Diffusion Models for Video Editing
  34. CVPR 2026SAGE Training Smart Any-Horizon Agents for Long Video Reasoning with
  35. CVPR 2026SAVE Speech-Aware Video Representation Learning for Video-Text Retrieval
  36. CVPR 2026Scaling Zero-Shot Reference-to-Video Generation
  37. CVPR 2026Scaling4D Pushing the Frontier of Video Novel View Synthesis through
  38. CVPR 2026SceneScribe-1M A Large-Scale Video Dataset with Comprehensive Geometric and Semantic
  39. CVPR 2026Score2Instruct Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring
  40. CVPR 2026SEASON Mitigating Temporal Hallucination in Video Large Language Models via
  41. CVPR 2026SeeThrough3D Occlusion Aware 3D Control in Text-to-Image Generation
  42. CVPR 2026Self-Critical Distillation Network for Video-based Commonsense Captioning
  43. CVPR 2026Self-Evaluation Unlocks Any-Step Text-to-Image Generation
  44. CVPR 2026ShotDirector Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
  45. CVPR 2026Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
  46. CVPR 2026SLVMEval Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
  47. CVPR 2026SMRABooth Subject and Motion Representation Alignment for Customized Video Generation
  48. CVPR 2026Spatia Video Generation with Updatable Spatial Memory
  49. CVPR 2026SpatialVID A Large-Scale Video Dataset with Spatial Annotations
  50. CVPR 2026SPDMark Selective Parameter Displacement for Robust Video Watermarking

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