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

198 papers, page 3 of 4

101. CVPR 2026MovieRecapsQA A Multimodal Open-Ended Video Question-Answering Benchmark
102. CVPR 2026Multi-level Causal LLM-based Text-to-Motion Generation with Human Alignment
103. CVPR 2026MultiBanana A Challenging Benchmark for Multi-Reference Text-to-Image Generation
104. CVPR 2026MultiShotMaster A Controllable Multi-Shot Video Generation Framework
105. CVPR 2026Next-Scale Autoregressive Models for Text-to-Motion Generation
106. CVPR 2026Omni2Sound Towards Unified Video-Text-to-Audio Generation
107. CVPR 2026OneStory Coherent Multi-Shot Video Generation with Adaptive Memory
108. CVPR 2026ORBIT Benchmarking SfM in the Wild with 360deg Video
109. CVPR 2026ORV 4D Occupancy-centric Robot Video Generation
110. CVPR 2026OSPO Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation
111. CVPR 2026PAM A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation
112. CVPR 2026Pantheon360 Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusion
113. CVPR 2026ParTY Part-Guidance for Expressive Text-to-Motion Synthesis
114. CVPR 2026Physical Simulator In-the-Loop Video Generation
115. CVPR 2026PhysVid Physics Aware Local Conditioning for Generative Video Models
116. CVPR 2026Plenoptic Video Generation
117. CVPR 2026PoseAnything General Pose-guided Video Generation with Part-aware Temporal Coherence
118. CVPR 2026Property-Informed Diffusion-Based Text-to-Microstructure Generation
119. CVPR 2026PS-SR Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
120. CVPR 2026PyraTok Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
121. CVPR 2026Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep
122. CVPR 2026Reasoning Diffusion for Unpaired Test Time Out-of-distribution Text-Image to Video
123. CVPR 2026RecEdit-Drive 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes
124. CVPR 2026Reconstruction-Guided Slot Curriculum Addressing Object Over-Fragmentation in Video Object-Centric Learning
125. CVPR 2026ReDirector Creating Any-Length Video Retakes with Rotary Camera Encoding
126. CVPR 2026Ref4D-VideoBench Four-Dimensional Reference-Based Evaluation of Text-to-Video Generative Models
127. CVPR 2026Relightful Video Portrait Harmonization
128. CVPR 2026Residual Decoder Adapter ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
129. CVPR 2026Resolving the Identity Crisis in Text-to-Image Generation
130. CVPR 2026Restore Text First Enhance Image Later Two-Stage Scene Text Image
131. CVPR 2026Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
132. CVPR 2026Reward Forcing Efficient Streaming Video Generation with Rewarded Distribution Matching
133. CVPR 2026RFDM Residual Flow Diffusion Models for Video Editing
134. CVPR 2026SAGE Training Smart Any-Horizon Agents for Long Video Reasoning with
135. CVPR 2026SAVE Speech-Aware Video Representation Learning for Video-Text Retrieval
136. CVPR 2026Scaling Zero-Shot Reference-to-Video Generation
137. CVPR 2026Scaling4D Pushing the Frontier of Video Novel View Synthesis through
138. CVPR 2026SceneScribe-1M A Large-Scale Video Dataset with Comprehensive Geometric and Semantic
139. CVPR 2026Score2Instruct Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring
140. CVPR 2026SEASON Mitigating Temporal Hallucination in Video Large Language Models via
141. CVPR 2026SeeThrough3D Occlusion Aware 3D Control in Text-to-Image Generation
142. CVPR 2026Self-Critical Distillation Network for Video-based Commonsense Captioning
143. CVPR 2026Self-Evaluation Unlocks Any-Step Text-to-Image Generation
144. CVPR 2026ShotDirector Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
145. CVPR 2026Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
146. CVPR 2026SLVMEval Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
147. CVPR 2026SMRABooth Subject and Motion Representation Alignment for Customized Video Generation
148. CVPR 2026Spatia Video Generation with Updatable Spatial Memory
149. CVPR 2026SpatialVID A Large-Scale Video Dataset with Spatial Annotations
150. CVPR 2026SPDMark Selective Parameter Displacement for Robust Video Watermarking

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.