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

209 papers, page 2 of 5

51. ICLR 2026MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation
52. ICLR 2026MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
53. ICLR 2026MotionStream: Real-Time Video Generation with Interactive Motion Controls
54. ICLR 2026MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation
55. ICLR 2026NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation
56. ICLR 2026Neodragon: Mobile Video Generation Using Diffusion Transformer
57. ICLR 2026NeRV-Diffusion: Diffuse Implicit Neural Representation for Video Synthesis
58. ICLR 2026NewtonGen: Physics-consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics
59. ICLR 2026Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset
60. ICLR 2026Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
61. ICLR 2026ReactID: Synchronizing Realistic Actions and Identity in Personalized Video Generation
62. ICLR 2026Real-Time Motion-Controllable Autoregressive Video Diffusion
63. ICLR 2026Revisiting Global Text Conditioning in Diffusion Transformers
64. ICLR 2026Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts
65. ICLR 2026Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
66. ICLR 2026SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
67. ICLR 2026Scale-wise Distillation of Diffusion Models
68. ICLR 2026Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
69. ICLR 2026SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
70. ICLR 2026SimpleGVR: A Simple Baseline for Latent-Cascaded Generative Video Super-Resolution
71. ICLR 2026Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
72. ICLR 2026SteinsGate: Adding Causality to Diffusions for Long Video Generation via Path Integral
73. ICLR 2026Target-Aware Video Diffusion Models
74. ICLR 2026Text summarization via global structure awareness
75. ICLR 2026Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator
76. ICLR 2026Time-to-Move: Training-Free Motion-Controlled Video Generation via Dual-Clock Denoising
77. ICLR 2026ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
78. ICLR 2026Towards One-step Causal Video Generation via Adversarial Self-Distillation
79. ICLR 2026TPDiff: Temporal Pyramid Video Diffusion Model
80. ICLR 2026Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer
81. ICLR 2026TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation
82. ICLR 2026TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
83. ICLR 2026TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
84. ICLR 2026UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers
85. ICLR 2026Unified In-Context Video Editing
86. ICLR 2026Uniform Discrete Diffusion with Metric Path for Video Generation
87. ICLR 2026Video Unlearning via Low-Rank Refusal Vector
88. ICLR 2026Video-As-Prompt: Unified Semantic Control for Video Generation
89. ICLR 2026VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
90. ICLR 2026Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
91. ICLR 2026VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
92. ICLR 2026VMoBA: Mixture-of-Block Attention for Video Diffusion Models
93. ICLR 2026Weak-to-Strong Diffusion
94. ICLR 2026WoW!: World Models in a Closed-Loop World
95. ICLR 20253DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
96. ICLR 20254K4DGen: Panoramic 4D Generation at 4K Resolution
97. ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
98. ICLR 2025Animate-X: Universal Character Image Animation with Enhanced Motion Representation
99. ICLR 2025ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation
100. ICLR 2025Autoregressive Video Generation without Vector Quantization

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.