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

448 papers, page 2 of 9

51. CVPR 2026EgoControl Controllable Egocentric Video Generation via 3D Full-Body Poses
52. CVPR 2026EgoX Egocentric Video Generation from a Single Exocentric Video
53. CVPR 2026Elastic3D Controllable Stereo Video Conversion with Guided Latent Decoding
54. CVPR 2026ELV-Halluc Benchmarking Semantic Aggregation Hallucinations in Video Understanding
55. CVPR 2026Endless World Real-Time 3D-Aware Long Video Generation
56. CVPR 2026EVATok Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
57. CVPR 2026EvoID Reinforced Evolution for Identity-Preserving Video Generation
58. CVPR 2026ExPose Reinforcing Video Generation Models for Extreme Pose Estimation
59. CVPR 2026First Frame Is the Place to Go for Video Content
60. CVPR 2026FlashMotion Few-Step Controllable Video Generation with Trajectory Guidance
61. CVPR 2026FlexTraj Image-to-Video Generation with Flexible Point Trajectory Control
62. CVPR 2026Flowception Temporally Expansive Flow Matching for Video Generation
63. CVPR 2026FlowDirector Training-Free Flow Steering for Precise Text-to-Video Editing
64. CVPR 2026Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction
65. CVPR 2026GenColorBench A Color Evaluation Benchmark for Text-to-Image Generation
66. CVPR 2026Generalizable Video Quality Assessment via Weak-to-Strong Learning
67. CVPR 2026Geometry-as-context Modulating Explicit 3D in Scene-consistent Video Generation to Geometry
68. CVPR 2026Gloria Consistent Character Video Generation via Content Anchors
69. CVPR 2026Goal Force Teaching Video Models To Accomplish Physics-Conditioned Goals
70. CVPR 2026Gravitation-Driven Semantic Alignment for Text Video Retrieval
71. CVPR 2026Gyro-based Deep Video Deblurring
72. CVPR 2026HandDreamer Zero-Shot Text to 3D Hand Model Generation using Corrective
73. CVPR 2026HandWorld Hand-Centric Unified Video Action Generation
74. CVPR 2026Hear What Matters Text-conditioned Selective Video-to-Audio Generation
75. CVPR 2026HieraMamba Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling
76. CVPR 2026Hierarchical Codec Diffusion for Video-to-Speech Generation
77. CVPR 2026Hierarchical Enhancement of Semantic Priors for Disentangled Text-Driven Motion Generation
78. CVPR 2026High Resolution Neural Video Coding with Bi-directional Confidence-Guided Reference Information
79. CVPR 2026HoloCine Holistic Generation of Cinematic Multi-Shot Long Video Narratives
80. CVPR 2026ID-Crafter VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
81. CVPR 2026Imagine Before Concentration Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
82. CVPR 2026Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
83. CVPR 2026Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
84. CVPR 2026Infinity-RoPE Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
85. CVPR 2026InternVideo-Next Towards World-Understanding Video Models
86. CVPR 2026IVAAN Instance-level Vision-Language Alignment via Attribute-Guided Text Prompts Generation for
87. CVPR 2026LAMP Language-Assisted Motion Planning for Controllable Video Generation
88. CVPR 2026LaVR Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large
89. CVPR 2026Learning Effective Sign Features without Text for Gloss-free Sign Language
90. CVPR 2026Less is More Data-Efficient Adaptation for Controllable Text-to-Video Generation
91. CVPR 2026Lighting-grounded Video Generation with Renderer-based Agent Reasoning
92. CVPR 2026LinVideo A Post-Training Framework towards On Attention in Efficient Video
93. CVPR 2026LoL Longer than Longer Scaling Video Generation to Hour
94. CVPR 2026LRHDR Learning Representation-enhanced HDR Video Reconstruction
95. CVPR 2026Lynx Towards High-Fidelity Personalized Video Generation
96. CVPR 2026M4V Multimodal Mamba for Efficient Text-to-Video Generation
97. CVPR 2026Minerva-Ego Spatiotemporal Hints for Egocentric Video Understanding
98. CVPR 2026MoLingo Motion-Language Alignment for Text-to-Human Motion Generation
99. CVPR 2026MotionHiFlow Text-to-Motion via Hierarchical Flow Matching
100. CVPR 2026MotionV2V Editing Motion in a Video

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.