Text-to-Video papers, 2023–2026

Key findings

• Text-to-Video went from 170 papers in 2023 to 448 in 2026, roughly 2.6x in three years.
• CVPR publishes the most Text-to-Video work: 574 papers from 2023 to 2026, 48% of the four-venue total.
• The fastest-growing overlap is with Deep learning · generative models and autoencoders: papers tagged with both rose from 2 in 2023 to 26 in 2026.
• Among the 5 topics under Multimodal Generation, it ranks #1 by 2026 paper count; the fastest grower in the group, Storytelling Generation, is up 15x versus 2.6x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Text-to-Video papers

247 papers, page 2 of 5

51. CVPR 2024InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning
52. CVPR 2024InstructVideo: Instructing Video Diffusion Models with Human Feedback
53. CVPR 2024JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
54. CVPR 2024Koala: Key Frame-Conditioned Long Video-LLM
55. CVPR 2024KVQ: Kwai Video Quality Assessment for Short-form Videos
56. CVPR 2024LAMP: Learn A Motion Pattern for Few-Shot Video Generation
57. CVPR 2024Learned Scanpaths Aid Blind Panoramic Video Quality Assessment
58. CVPR 2024Learning Continuous 3D Words for Text-to-Image Generation
59. CVPR 2024Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
60. CVPR 2024Learning from One Continuous Video Stream
61. CVPR 2024Learning Multi-Dimensional Human Preference for Text-to-Image Generation
62. CVPR 2024Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering
63. CVPR 2024LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation
64. CVPR 2024LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching
65. CVPR 2024Make Pixels Dance: High-Dynamic Video Generation
66. CVPR 2024Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text
67. CVPR 2024MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
68. CVPR 2024MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers
69. CVPR 2024MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation
70. CVPR 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis
71. CVPR 2024Modular Blind Video Quality Assessment
72. CVPR 2024MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video
73. CVPR 2024MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation
74. CVPR 2024MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild
75. CVPR 2024MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval
76. CVPR 2024Neighbor Relations Matter in Video Scene Detection
77. CVPR 2024Neural Video Compression with Feature Modulation
78. CVPR 2024NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation
79. CVPR 2024OmniViD: A Generative Framework for Universal Video Understanding
80. CVPR 2024On the Content Bias in Frechet Video Distance
81. CVPR 2024On the Scalability of Diffusion-based Text-to-Image Generation
82. CVPR 2024OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
83. CVPR 2024OTE: Exploring Accurate Scene Text Recognition Using One Token
84. CVPR 2024PEEKABOO: Interactive Video Generation via Masked-Diffusion
85. CVPR 2024Perception-Oriented Video Frame Interpolation via Asymmetric Blending
86. CVPR 2024Personalized Residuals for Concept-Driven Text-to-Image Generation
87. CVPR 2024PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion
88. CVPR 2024Point-VOS: Pointing Up Video Object Segmentation
89. CVPR 2024PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild
90. CVPR 2024REACTO: Reconstructing Articulated Objects from a Single Video
91. CVPR 2024Rich Human Feedback for Text-to-Image Generation
92. CVPR 2024Scaling Up Video Summarization Pretraining with Large Language Models
93. CVPR 2024Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
94. CVPR 2024Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization
95. CVPR 2024Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
96. CVPR 2024Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior
97. CVPR 2024SimDA: Simple Diffusion Adapter for Efficient Video Generation
98. CVPR 2024SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers
99. CVPR 2024SnAG: Scalable and Accurate Video Grounding
100. CVPR 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis

FAQ

How many Text-to-Video papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,185 in total: 170 in 2023, 247 in 2024, 320 in 2025, 448 in 2026.

How many Text-to-Video papers are at NeurIPS 2026?

NeurIPS 2026 has 101 Text-to-Video papers, versus 91 the year before.

How many Text-to-Video papers are at ICLR 2026?

ICLR 2026 has 94 Text-to-Video papers, versus 59 the year before.

How many Text-to-Video papers are at ICML 2026?

ICML 2026 has 55 Text-to-Video papers, versus 14 the year before.

How many Text-to-Video papers are at CVPR 2026?

CVPR 2026 has 198 Text-to-Video papers, versus 156 the year before.

Which conference publishes the most Text-to-Video papers?

CVPR, with 574 papers from 2023 to 2026.