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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 52 | 21 | 17 | 80 | 170 |
| 2024 | 55 | 35 | 17 | 140 | 247 |
| 2025 | 91 | 59 | 14 | 156 | 320 |
| 2026 | 101 | 94 | 55 | 198 | 448 |
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 574 篇，第 4 / 12 页
- CVPR 2026STCDiT Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution
- CVPR 2026Stereo World Model Camera-Guided Stereo Video Generation
- CVPR 2026StereoWorld Geometry-Aware Monocular-to-Stereo Video Generation
- CVPR 2026Stitch-a-Demo Creating Video Demonstrations from Multistep Descriptions
- CVPR 2026StreamDiT Real-Time Streaming Text-to-Video Generation
- CVPR 2026StyleTextGen Style-Conditioned Multilingual Scene Text Generation
- CVPR 2026SURF Signature-Retained Fast Video Generation
- CVPR 2026SVBench Evaluation of Video Generation Models on Social Reasoning
- CVPR 2026SwitchCraft Training-Free Multi-Event Video Generation with Attention Controls
- CVPR 2026T2SGrid Temporal-to-Spatial Gridification for Video Temporal Grounding
- CVPR 2026TEAR Temporal-aware Automated Red-teaming for Text-to-Video Models
- CVPR 2026TempoControl Temporal Attention Guidance for Text-to-Video Models
- CVPR 2026TempoMaster Efficient Long Video Generation via Next-Frame-Rate Prediction
- CVPR 2026Text-Driven 3D Hand Motion Generation from Sign Language Data
- CVPR 2026Text-Image Conditioned 3D Generation
- CVPR 2026TextOVSR Text-Guided Real-World Opera Video Super-Resolution
- CVPR 2026Texvent Asynchronous Event Data Simulation via Text Prompt
- CVPR 2026TF-CADE Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection
- CVPR 2026TGT Text-Grounded Trajectories for Locally Controlled Video Generation
- CVPR 2026The devil is in the details Enhancing Video Virtual Try-On
- CVPR 2026Thinking with Frames Generative Video Distortion Evaluation via Frame Reward
- CVPR 2026Thinking with Video Video Generation as a Promising Multimodal Reasoning
- CVPR 2026Time Blindness Why Video-Language Models Cant See What Humans Can
- CVPR 2026TiViBench Benchmarking Think-in-Video Reasoning for Video Generation
- CVPR 2026Towards Training-free Scene Text Editing
- CVPR 2026Training-free Motion Factorization for Compositional Video Generation
- CVPR 2026Transition Matching Distillation for Fast Video Generation
- CVPR 2026TV2TV A Unified Framework for Interleaved Language and Video Generation
- CVPR 2026UFVideo Towards Unified Fine-Grained Video Cooperative Understanding with Large Language
- CVPR 2026Ultra-Fast Neural Video Compression
- CVPR 2026UltraFlux Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across
- CVPR 2026UniComp Rethinking Video Compression Through Informational Uniqueness
- CVPR 2026Unified Camera Positional Encoding for Controlled Video Generation
- CVPR 2026Unified Number-Free Text-to-Motion Generation Via Flow Matching
- CVPR 2026Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
- CVPR 2026Unleashing Vision-Language Semantics for Deepfake Video Detection
- CVPR 2026V-DPM 4D Video Reconstruction with Dynamic Point Maps
- CVPR 2026V-RGBX Video Editing with Accurate Controls over Intrinsic Properties
- CVPR 2026VDFE Difference-Aware 3D Scene Editing with Non-Intrusive Video Diffusion Priors
- CVPR 2026VDOT Efficient Unified Video Creation via Optimal Transport Distillation
- CVPR 2026Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner
- CVPR 2026Video-Only ToM Enhancing Theory of Mind in Multimodal Large Language
- CVPR 2026VidTAG Temporally Aligned Video to GPS Geolocalization with Denoising Sequence
- CVPR 2026VISTA A Test-Time Self-Improving Video Generation Agent
- CVPR 2026Vista4D Video Reshooting with 4D Point Clouds
- CVPR 2026When Anonymity Breaks Identifying Models Behind Text-to-Image Leaderboards
- CVPR 2026Where Culture Fades Revealing the Cultural Gap in Text-to-Image Generation
- CVPR 2026Yume1.5 A Text-Controlled Interactive World Generation Model
- CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
- CVPR 20254Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion
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"}
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。