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 9 of 24

401. NeurIPS 2026MonarchRT: Efficient Attention for Real-Time Video Generation
402. NeurIPS 2026MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
403. NeurIPS 2026Not Another Text Benchmark: Putting the “Visual" Back in Visual Question Answering for Large Video Models
404. NeurIPS 2026On Length Bias in EEG-to-Text Decoding
405. NeurIPS 2026OpenCoF: Learning to Reason Through Video Generation
406. NeurIPS 2026OptiWorld: Optimal Control for Video World Generation under Physical Constraints
407. NeurIPS 2026Parameterized Stripe Attention for Efficient Video Generation
408. NeurIPS 2026PARE: Pruning and Adaptive Routing for Efficient Video Generation
409. NeurIPS 2026PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
410. NeurIPS 2026PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
411. NeurIPS 2026Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment
412. NeurIPS 2026PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
413. NeurIPS 2026RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
414. NeurIPS 2026Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
415. NeurIPS 2026RECIPE: Procedural Planning via Grounding in Instructional Video
416. NeurIPS 2026Recreating Video Arenas via Automated Preference Scoring
417. NeurIPS 2026RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video
418. NeurIPS 2026Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
419. NeurIPS 2026RobustStress: Stress-Testing AI-Generated Text Detectors under Gradual Perturbations
420. NeurIPS 2026Seed-Your-Motion: Householder Orthogonal Noise for Motion-Controllable Video Diffusion Models
421. NeurIPS 2026Seeing the Unseen: Unified Visible–Invisible Motion for Physically Consistent Video Generation
422. NeurIPS 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
423. NeurIPS 2026Slide P2V-Bench: A Cross-Domain Benchmark for Slide-Centric Scientific Paper-to-Presentation Video Generation
424. NeurIPS 2026SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
425. NeurIPS 2026Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
426. NeurIPS 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
427. NeurIPS 2026Spatially-Grounded Long Video Generation with Self Geometry Forcing
428. NeurIPS 2026SteerVTE: Seamless Video Text Editing with Style and Glyph Control
429. NeurIPS 2026SynBench: A Benchmark for Differentially Private Text Generation
430. NeurIPS 2026Temporal Concentration from Rollout Errors: Implicit Preference Optimization For Text-to-Video Diffusion
431. NeurIPS 2026TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
432. NeurIPS 2026Text-to-CAD Evaluation with CADTests
433. NeurIPS 2026Towards Generalizable Partially Relevant Video Retrieval
434. NeurIPS 2026TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation
435. NeurIPS 2026TriTD: Tri-Partite Trajectory–Distribution Distillation for Real-Time Autoregressive Video Generation
436. NeurIPS 2026Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
437. NeurIPS 2026V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
438. NeurIPS 2026V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion
439. NeurIPS 2026Video Generation Research Needs a Legally Sustainable Data Infrastructure
440. NeurIPS 2026Video Stitching from Multiple Moving Cameras
441. NeurIPS 2026VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy Flywheel
442. NeurIPS 2026ViDiC: Video Difference Captioning
443. NeurIPS 2026VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval
444. NeurIPS 2026View-Spectral Reconciliation Learning for Text-based Multispectral Aerial–Ground Person Re-Identification
445. NeurIPS 2026ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
446. NeurIPS 2026Viverra: Text-to-Code with Guarantees
447. NeurIPS 2026What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting
448. NeurIPS 2026When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
449. CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
450. CVPR 20254Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion

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.