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

1,185 papers, page 14 of 24

651. ICLR 2025T2V-Turbo-v2: Enhancing Video Model Post-Training through Data, Reward, and Conditional Guidance Design
652. ICLR 2025TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
653. ICLR 2025Temporal Reasoning Transfer from Text to Video
654. ICLR 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
655. ICLR 2025Trajectory attention for fine-grained video motion control
656. ICLR 2025TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
657. ICLR 2025VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
658. ICLR 2025ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler
659. ICLR 2025Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
660. ICLR 2025VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing
661. ICLR 2025VideoPhy: Evaluating Physical Commonsense for Video Generation
662. ICLR 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
663. ICLR 2025VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
664. ICML 2025AdaWorld: Learning Adaptable World Models with Latent Actions
665. ICML 2025Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners
666. ICML 2025Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
667. ICML 2025Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification
668. ICML 2025Fast Video Generation with Sliding Tile Attention
669. ICML 2025FlexiClip: Locality-Preserving Free-Form Character Animation
670. ICML 2025GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
671. ICML 2025How to Synthesize Text Data without Model Collapse?
672. ICML 2025Imitation Learning from a Single Temporally Misaligned Video
673. ICML 2025MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
674. ICML 2025One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
675. ICML 2025Reflection-Window Decoding: Text Generation with Selective Refinement
676. ICML 2025Structure-Guided Large Language Models for Text-to-SQL Generation
677. ICML 2025Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
678. NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
679. NeurIPS 2025Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
680. NeurIPS 2025Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
681. NeurIPS 2025Asymmetric Dual-Lens Video Deblurring
682. NeurIPS 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
683. NeurIPS 2025CSGO: Content-Style Composition in Text-to-Image Generation
684. NeurIPS 2025Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation
685. NeurIPS 2025DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
686. NeurIPS 2025Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
687. NeurIPS 2025Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
688. NeurIPS 2025DisMo: Disentangled Motion Representations for Open-World Motion Transfer
689. NeurIPS 2025DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
690. NeurIPS 2025Don’t Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
691. NeurIPS 2025Dynamic Shadow Unveils Invisible Semantics for Video Outpainting
692. NeurIPS 2025EchoShot: Multi-Shot Portrait Video Generation
693. NeurIPS 2025Emergent Temporal Correspondences from Video Diffusion Transformers
694. NeurIPS 2025Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
695. NeurIPS 2025Faster Video Diffusion with Trainable Sparse Attention
696. NeurIPS 2025FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
697. NeurIPS 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation
698. NeurIPS 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
699. NeurIPS 2025Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
700. NeurIPS 2025From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos

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.