Deep learning · generative models and autoencoders papers, 2023–2026

Key findings

• Deep learning · generative models and autoencoders went from 1,216 papers in 2023 to 1,430 in 2026, roughly 1.2x in three years.
• NeurIPS publishes the most Deep learning · generative models and autoencoders work: 1,714 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with Image Generation: papers tagged with both rose from 35 in 2023 to 150 in 2026.
• Among the 11 topics under Deep Learning, it ranks #2 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Critical $\beta$-Scale for Posterior Collapse in Dirichlet $\beta$-VAEs
• ICML 2026(1D) Ordered Tokens Enable Efficient Test-Time Search
• ICLR 2026``Noisier'’ Noise Contrastive Estimation is (Almost) Maximum Likelihood
• CVPR 2026Anchoring and Rescaling Attention for Semantically Coherent Inbetweening
• NeurIPS 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness
• ICML 2025A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
• ICLR 2025A Watermark for Order-Agnostic Language Models
• CVPR 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
• NeurIPS 2024[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
• ICML 2024A Fixed-Point Approach for Causal Generative Modeling
• ICLR 2024$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
• CVPR 2024Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
• NeurIPS 2023(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
• ICML 2023A Kernelized Stein Discrepancy for Biological Sequences
• ICLR 2023Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
• ICML 2026$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
• ICLR 2026Analyzing and Evaluating Unbiased Language Model Watermark
• CVPR 2026Bidirectional Normalizing Flow From Data to Noise and Back

All Deep learning · generative models and autoencoders papers

4,314 papers, page 46 of 87

2251. NeurIPS 2025Prohibiting Generative AI in any Form of Weapon Control
2252. NeurIPS 2025Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
2253. NeurIPS 2025Random Forest Autoencoders for Guided Representation Learning
2254. NeurIPS 2025Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"
2255. NeurIPS 2025ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection
2256. NeurIPS 2025ReDi: Rectified Discrete Flow
2257. NeurIPS 2025REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
2258. NeurIPS 2025RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis
2259. NeurIPS 2025Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws
2260. NeurIPS 2025RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching
2261. NeurIPS 2025RGB-to-Polarization Estimation: A New Task and Benchmark Study
2262. NeurIPS 2025Riemannian Consistency Model
2263. NeurIPS 2025Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry
2264. NeurIPS 2025Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments
2265. NeurIPS 2025RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
2266. NeurIPS 2025ROGR: Relightable 3D Objects using Generative Relighting
2267. NeurIPS 2025Rotary Masked Autoencoders are Versatile Learners
2268. NeurIPS 2025SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
2269. NeurIPS 2025Salient Concept-Aware Generative Data Augmentation
2270. NeurIPS 2025Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures
2271. NeurIPS 2025Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation
2272. NeurIPS 2025Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
2273. NeurIPS 2025Scalable In-context Ranking with Generative Models
2274. NeurIPS 2025Scaling Offline RL via Efficient and Expressive Shortcut Models
2275. NeurIPS 2025Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres
2276. NeurIPS 2025SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
2277. NeurIPS 2025Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models
2278. NeurIPS 2025Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology
2279. NeurIPS 2025SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval
2280. NeurIPS 2025Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoders
2281. NeurIPS 2025ShapeEmbed: a self-supervised learning framework for 2D contour quantification
2282. NeurIPS 2025Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
2283. NeurIPS 2025Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression
2284. NeurIPS 2025Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative Modeling
2285. NeurIPS 2025SOMBRL: Scalable and Optimistic Model-Based RL
2286. NeurIPS 2025Space Group Equivariant Crystal Diffusion
2287. NeurIPS 2025SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
2288. NeurIPS 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
2289. NeurIPS 2025SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
2290. NeurIPS 2025Spectral Conditioning of Attention Improves Transformer Performance
2291. NeurIPS 2025Stability and Oracle Inequalities for Optimal Transport Maps between General Distributions
2292. NeurIPS 2025Steering Generative Models with Experimental Data for Protein Fitness Optimization
2293. NeurIPS 2025StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models
2294. NeurIPS 2025StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
2295. NeurIPS 2025SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
2296. NeurIPS 2025System-Embedded Diffusion Bridge Models
2297. NeurIPS 2025Taming generative video models for zero-shot optical flow extraction
2298. NeurIPS 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
2299. NeurIPS 2025TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer
2300. NeurIPS 2025The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models

FAQ

How many Deep learning · generative models and autoencoders papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

4,314 in total: 1,216 in 2023, 768 in 2024, 900 in 2025, 1,430 in 2026.

How many Deep learning · generative models and autoencoders papers are at NeurIPS 2026?

NeurIPS 2026 has 349 Deep learning · generative models and autoencoders papers, versus 240 the year before.

How many Deep learning · generative models and autoencoders papers are at ICLR 2026?

ICLR 2026 has 303 Deep learning · generative models and autoencoders papers, versus 275 the year before.

How many Deep learning · generative models and autoencoders papers are at ICML 2026?

ICML 2026 has 604 Deep learning · generative models and autoencoders papers, versus 275 the year before.

How many Deep learning · generative models and autoencoders papers are at CVPR 2026?

CVPR 2026 has 174 Deep learning · generative models and autoencoders papers, versus 110 the year before.

Which conference publishes the most Deep learning · generative models and autoencoders papers?

NeurIPS, with 1,714 papers from 2023 to 2026.