Image Generation papers, 2023–2026

Key findings

• Image Generation went from 780 papers in 2023 to 1,721 in 2026, roughly 2.2x in three years.
• CVPR publishes the most Image Generation work: 2,262 papers from 2023 to 2026, 44% of the four-venue total.
• The fastest-growing overlap is with Deep learning · generative models and autoencoders: papers tagged with both rose from 35 in 2023 to 150 in 2026.
• Among the 5 topics under Computer Vision, it ranks #1 by 2026 paper count; the fastest grower in the group, Video Understanding, is up 2.6x versus 2.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026Klein Hyperbolic Metric Learning
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks
• NeurIPS 2025Alchemist: Turning Public Text-to-Image Data into Generative Gold
• ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
• ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
• CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
• NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
• ICML 2024Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
• ICLR 2024AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
• CVPR 2024DemoCaricature: Democratising Caricature Generation with a Rough Sketch
• NeurIPS 20234D Panoptic Scene Graph Generation
• ICML 2023Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
• ICLR 2023Accurate Image Restoration with Attention Retractable Transformer
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
• ICLR 2026All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
• CVPR 2026AIMDepth Asymmetric Image-Event Mamba for Monocular Depth Estimation

All Image Generation papers

430 papers, page 9 of 9

401. NeurIPS 2025Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
402. NeurIPS 2025Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
403. NeurIPS 2025Unified all-atom molecule generation with neural fields
404. NeurIPS 2025UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
405. NeurIPS 2025Universal Few-shot Spatial Control for Diffusion Models
406. NeurIPS 2025Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator
407. NeurIPS 2025Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation
408. NeurIPS 2025URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training
409. NeurIPS 2025VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image
410. NeurIPS 2025VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
411. NeurIPS 2025vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models
412. NeurIPS 2025Video Perception Models for 3D Scene Synthesis
413. NeurIPS 2025VideoMAR: Autoregressive Video Generation with Continuous Tokens
414. NeurIPS 2025VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
415. NeurIPS 2025ViewCraft3D: High-fidelity and View-Consistent 3D Vector Graphics Synthesis
416. NeurIPS 2025Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning
417. NeurIPS 2025Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image
418. NeurIPS 2025Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
419. NeurIPS 2025Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation
420. NeurIPS 2025VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
421. NeurIPS 2025VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
422. NeurIPS 2025Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
423. NeurIPS 2025Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
424. NeurIPS 2025WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting
425. NeurIPS 2025Watermarking Autoregressive Image Generation
426. NeurIPS 2025When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization
427. NeurIPS 2025WISA: World simulator assistant for physics-aware text-to-video generation
428. NeurIPS 2025X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability
429. NeurIPS 2025XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
430. NeurIPS 2025ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

FAQ

How many Image Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

5,184 in total: 780 in 2023, 1,216 in 2024, 1,467 in 2025, 1,721 in 2026.

How many Image Generation papers are at NeurIPS 2026?

NeurIPS 2026 has 453 Image Generation papers, versus 430 the year before.

How many Image Generation papers are at ICLR 2026?

ICLR 2026 has 349 Image Generation papers, versus 278 the year before.

How many Image Generation papers are at ICML 2026?

ICML 2026 has 230 Image Generation papers, versus 147 the year before.

How many Image Generation papers are at CVPR 2026?

CVPR 2026 has 689 Image Generation papers, versus 612 the year before.

Which conference publishes the most Image Generation papers?

CVPR, with 2,262 papers from 2023 to 2026.