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

320 papers, page 2 of 7

51. CVPR 2025Goku: Flow Based Video Generative Foundation Models
52. CVPR 2025GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking
53. CVPR 2025High-Fidelity Relightable Monocular Portrait Animation with Lighting-Controllable Video Diffusion Model
54. CVPR 2025HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation
55. CVPR 2025HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion
56. CVPR 2025HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks
57. CVPR 2025Identity-Preserving Text-to-Video Generation by Frequency Decomposition
58. CVPR 2025IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner
59. CVPR 2025Improved Video VAE for Latent Video Diffusion Model
60. CVPR 2025InsTaG: Learning Personalized 3D Talking Head from Few-Second Video
61. CVPR 2025InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
62. CVPR 2025InterDyn: Controllable Interactive Dynamics with Video Diffusion Models
63. CVPR 2025Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation
64. CVPR 2025Keyframe-Guided Creative Video Inpainting
65. CVPR 2025Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content
66. CVPR 2025Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval
67. CVPR 2025Learning from Streaming Video with Orthogonal Gradients
68. CVPR 2025Learning Temporally Consistent Video Depth from Video Diffusion Priors
69. CVPR 2025Learning Visual Generative Priors without Text
70. CVPR 2025LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
71. CVPR 2025LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant
72. CVPR 2025LongDiff: Training-Free Long Video Generation in One Go
73. CVPR 2025Make It Count: Text-to-Image Generation with an Accurate Number of Objects
74. CVPR 2025MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
75. CVPR 2025Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation
76. CVPR 2025MatAnyone: Stable Video Matting with Consistent Memory Propagation
77. CVPR 2025Mimir: Improving Video Diffusion Models for Precise Text Understanding
78. CVPR 2025Mind the Time: Temporally-Controlled Multi-Event Video Generation
79. CVPR 2025Minority-Focused Text-to-Image Generation via Prompt Optimization
80. CVPR 2025Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking
81. CVPR 2025MotiF: Making Text Count in Image Animation with Motion Focal Loss
82. CVPR 2025Motion Prompting: Controlling Video Generation with Motion Trajectories
83. CVPR 2025MotionPro: A Precise Motion Controller for Image-to-Video Generation
84. CVPR 2025MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
85. CVPR 2025Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts
86. CVPR 2025MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation
87. CVPR 2025Multi-subject Open-set Personalization in Video Generation
88. CVPR 2025MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval
89. CVPR 2025Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions
90. CVPR 2025Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
91. CVPR 2025Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
92. CVPR 2025On the Consistency of Video Large Language Models in Temporal Comprehension
93. CVPR 2025One-Minute Video Generation with Test-Time Training
94. CVPR 2025OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
95. CVPR 2025OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
96. CVPR 2025Optical-Flow Guided Prompt Optimization for Coherent Video Generation
97. CVPR 2025OSV: One Step is Enough for High-Quality Image to Video Generation
98. CVPR 2025PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
99. CVPR 2025Perceptual Video Compression with Neural Wrapping
100. CVPR 2025PersonaBooth: Personalized Text-to-Motion Generation

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.