深度学习 · foundation models论文趋势 2023–2026

主要结论

• 深度学习 · foundation models论文从 2023 年的 72 篇增长到 2026 年的 177 篇，三年间扩大到约 2.5 倍。
• NeurIPS 是发深度学习 · foundation models论文最多的会议，2023–2026 年共 299 篇，占四个会议总量的 56%。
• 交叉方向里涨得最快的是基础模型适配：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 66 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 8；同组增长最快的扩散模型是 4.1 倍，深度学习 · foundation models是 2.5 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 2026Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
• ICML 2026ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized Domains
• ICLR 2026Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization
• CVPR 2026Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression
• NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation Models
• ICML 2025Contrastive Localized Language-Image Pre-Training
• ICLR 2025Revisiting Convolution Architecture in the Realm of DNA Foundation Models
• CVPR 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matching
• NeurIPS 2024$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
• ICML 2024Position: On the Societal Impact of Open Foundation Models
• CVPR 20243D-LFM: Lifting Foundation Model
• NeurIPS 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
• ICML 2023Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
• NeurIPS 2026Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
• ICML 2026Alethia: a Foundational Encoder for Voice Deepfakes
• ICLR 2026DND: Boosting Large Language Models with Dynamic Nested Depth
• CVPR 2026UniSER A Foundation Model for Unified Soft Effects Removal
• NeurIPS 2025ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data
• ICML 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
• ICLR 2025Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

全部深度学习 · foundation models论文

共 299 篇，第 2 / 6 页

51. NeurIPS 2024Adaptive Depth Networks with Skippable Sub-Paths
52. NeurIPS 2024Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
53. NeurIPS 2024Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
54. NeurIPS 2024Algebraic Positional Encodings
55. NeurIPS 2024Alias-Free Mamba Neural Operator
56. NeurIPS 2024AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
57. NeurIPS 2024Amortized Eigendecomposition for Neural Networks
58. NeurIPS 2024Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
59. NeurIPS 2024Are Self-Attentions Effective for Time Series Forecasting?
60. NeurIPS 2024Asynchronous Perception Machine for Efficient Test Time Training
61. NeurIPS 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
62. NeurIPS 2024B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
63. NeurIPS 2024BOLD: Boolean Logic Deep Learning
64. NeurIPS 2024Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
65. NeurIPS 2024Bridging the Divide: Reconsidering Softmax and Linear Attention
66. NeurIPS 2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
67. NeurIPS 2024Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
68. NeurIPS 2024CALANet: Cheap All-Layer Aggregation for Human Activity Recognition
69. NeurIPS 2024Calibrated Self-Rewarding Vision Language Models
70. NeurIPS 2024Can neural operators always be continuously discretized?
71. NeurIPS 2024CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
72. NeurIPS 2024Cell ontology guided transcriptome foundation model
73. NeurIPS 2024Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
74. NeurIPS 2024Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
75. NeurIPS 2024Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
76. NeurIPS 2024CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
77. NeurIPS 2024Compressing Large Language Models using Low Rank and Low Precision Decomposition
78. NeurIPS 2024CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting
79. NeurIPS 2024ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
80. NeurIPS 2024ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
81. NeurIPS 2024CosAE: Learnable Fourier Series for Image Restoration
82. NeurIPS 2024Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
83. NeurIPS 2024Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
84. NeurIPS 2024CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection
85. NeurIPS 2024D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
86. NeurIPS 2024D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
87. NeurIPS 2024DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
88. NeurIPS 2024DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations
89. NeurIPS 2024Demystify Mamba in Vision: A Linear Attention Perspective
90. NeurIPS 2024Dendritic Integration Inspired Artificial Neural Networks Capture Data Correlation
91. NeurIPS 2024Dense Associative Memory Through the Lens of Random Features
92. NeurIPS 2024DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
93. NeurIPS 2024DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
94. NeurIPS 2024Derivative-enhanced Deep Operator Network
95. NeurIPS 2024DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
96. NeurIPS 2024DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning
97. NeurIPS 2024DisCEdit: Model Editing by Identifying Discriminative Components
98. NeurIPS 2024Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
99. NeurIPS 2024Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks
100. NeurIPS 2024DOFEN: Deep Oblivious Forest ENsemble

常见问题

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

共 536 篇，按年份分别是 2023 年 72 篇、2024 年 209 篇、2025 年 78 篇、2026 年 177 篇。

NeurIPS 2026 有多少篇深度学习 · foundation models论文？

NeurIPS 2026 有 27 篇深度学习 · foundation models论文，上一届是 15 篇。

ICLR 2026 有多少篇深度学习 · foundation models论文？

ICLR 2026 有 8 篇深度学习 · foundation models论文，上一届是 6 篇。

ICML 2026 有多少篇深度学习 · foundation models论文？

ICML 2026 有 135 篇深度学习 · foundation models论文，上一届是 53 篇。

CVPR 2026 有多少篇深度学习 · foundation models论文？

CVPR 2026 有 7 篇深度学习 · foundation models论文，上一届是 4 篇。

哪个会议的深度学习 · foundation models论文最多？

NeurIPS，2023–2026 年共 299 篇。