深度学习 · generative models and autoencoders论文趋势 2023–2026

主要结论

• 深度学习 · generative models and autoencoders论文从 2023 年的 1,216 篇增长到 2026 年的 1,430 篇，三年间扩大到约 1.2 倍。
• NeurIPS 是发深度学习 · generative models and autoencoders论文最多的会议，2023–2026 年共 1,714 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是图像生成：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 150 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 2；同组增长最快的扩散模型是 4.1 倍，深度学习 · generative models and autoencoders是 1.2 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部深度学习 · generative models and autoencoders论文

共 1,430 篇，第 8 / 29 页

351. ICLR 2026Matched Data, Better Models: Target Aligned Data Filtering with Sparse Features
352. ICLR 2026Measurement Score-Based Diffusion Model
353. ICLR 2026MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
354. ICLR 2026Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains
355. ICLR 2026Mitigating Noise Shift in Denoising Generative Models with Noise Awareness Guidance
356. ICLR 2026Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment
357. ICLR 2026Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter
358. ICLR 2026MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling
359. ICLR 2026Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening
360. ICLR 2026Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
361. ICLR 2026Multiverse Mechanica: A Testbed for Learning Game Mechanics via Counterfactual Worlds
362. ICLR 2026MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
363. ICLR 2026MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion
364. ICLR 2026Navigating the Latent Space Dynamics of Neural Models
365. ICLR 2026NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
366. ICLR 2026Neyman-Pearson Classification under Both Null and Alternative Distributions Shift
367. ICLR 2026NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning
368. ICLR 2026NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
369. ICLR 2026On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
370. ICLR 2026On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy
371. ICLR 2026Online Black-Box Prompt Optimization with Regret Guarantees under Noisy Feedback
372. ICLR 2026Online Decision Making with Generative Action Sets
373. ICLR 2026Overshoot and Shrinkage in Classifier-Free Guidance: From Theory to Practice
374. ICLR 2026P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
375. ICLR 2026Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
376. ICLR 2026Partition Generative Modeling: Masked Modeling Without Masks
377. ICLR 2026Pixel-Perfect Puppetry: Precision-Guided Enhancement for Face Image and Video Editing
378. ICLR 2026PixNerd: Pixel Neural Field Diffusion
379. ICLR 2026Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization
380. ICLR 2026PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives
381. ICLR 2026Practical estimation of the optimal classification error with soft labels and calibration
382. ICLR 2026PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
383. ICLR 2026Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
384. ICLR 2026Pretraining Scaling Laws for Generative Evaluations of Language Models
385. ICLR 2026Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression
386. ICLR 2026Priors in time: Missing inductive biases for language model interpretability
387. ICLR 2026Product-Quantised Image Representation for High-Quality Image Synthesis
388. ICLR 2026PROTDYN: A FOUNDATION PROTEIN LANGUAGE MODEL FOR THERMODYNAMICS AND DYNAMICS GENERATION
389. ICLR 2026ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
390. ICLR 2026Provable Separations between Memorization and Generalization in Diffusion Models
391. ICLR 2026Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
392. ICLR 2026Quasi-Monte Carlo Methods Enable Extremely Low-Dimensional Deep Generative Models
393. ICLR 2026Quotient-Space Diffusion Model
394. ICLR 2026ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
395. ICLR 2026Riemannian Variational Flow Matching for Material and Protein Design
396. ICLR 2026RNE: plug-and-play diffusion inference-time control and energy-based training
397. ICLR 2026SAFER: Risk-Constrained Sample-then-Filter in Large Language Models
398. ICLR 2026Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
399. ICLR 2026Scaling Group Inference for Diverse and High-Quality Generation
400. ICLR 2026Scaling Sequence-to-Sequence Generative Neural Rendering

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · generative models and autoencoders论文？

共 4,314 篇，按年份分别是 2023 年 1,216 篇、2024 年 768 篇、2025 年 900 篇、2026 年 1,430 篇。

NeurIPS 2026 有多少篇深度学习 · generative models and autoencoders论文？

NeurIPS 2026 有 349 篇深度学习 · generative models and autoencoders论文，上一届是 240 篇。

ICLR 2026 有多少篇深度学习 · generative models and autoencoders论文？

ICLR 2026 有 303 篇深度学习 · generative models and autoencoders论文，上一届是 275 篇。

ICML 2026 有多少篇深度学习 · generative models and autoencoders论文？

ICML 2026 有 604 篇深度学习 · generative models and autoencoders论文，上一届是 275 篇。

CVPR 2026 有多少篇深度学习 · generative models and autoencoders论文？

CVPR 2026 有 174 篇深度学习 · generative models and autoencoders论文，上一届是 110 篇。

哪个会议的深度学习 · generative models and autoencoders论文最多？

NeurIPS，2023–2026 年共 1,714 篇。