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 209 篇，第 1 / 5 页

1. CVPR 20243D-LFM: Lifting Foundation Model
2. CVPR 2024Asymmetric Masked Distillation for Pre-Training Small Foundation Models
3. CVPR 2024Bridging Remote Sensors with Multisensor Geospatial Foundation Models
4. CVPR 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
5. CVPR 2024OpenEQA: Embodied Question Answering in the Era of Foundation Models
6. CVPR 2024Probing the 3D Awareness of Visual Foundation Models
7. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
8. ICML 2024Differentially Private Bias-Term Fine-tuning of Foundation Models
9. ICML 2024Foundation Policies with Hilbert Representations
10. ICML 2024Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
11. ICML 2024MOMENT: A Family of Open Time-series Foundation Models
12. ICML 2024Position: On the Societal Impact of Open Foundation Models
13. ICML 2024Position: Why Tabular Foundation Models Should Be a Research Priority
14. ICML 2024Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
15. ICML 2024Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
16. ICML 2024To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO
17. ICML 2024Transferring Knowledge From Large Foundation Models to Small Downstream Models
18. NeurIPS 2024$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
19. NeurIPS 2024$C^2M^3$: Cycle-Consistent Multi-Model Merging
20. NeurIPS 20243-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
21. NeurIPS 2024A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
22. NeurIPS 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecture
23. NeurIPS 2024Accelerating Transformers with Spectrum-Preserving Token Merging
24. NeurIPS 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
25. NeurIPS 2024AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
26. NeurIPS 2024Adaptive Depth Networks with Skippable Sub-Paths
27. NeurIPS 2024Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
28. NeurIPS 2024Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
29. NeurIPS 2024Algebraic Positional Encodings
30. NeurIPS 2024Alias-Free Mamba Neural Operator
31. NeurIPS 2024AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
32. NeurIPS 2024Amortized Eigendecomposition for Neural Networks
33. NeurIPS 2024Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
34. NeurIPS 2024Are Self-Attentions Effective for Time Series Forecasting?
35. NeurIPS 2024Asynchronous Perception Machine for Efficient Test Time Training
36. NeurIPS 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
37. NeurIPS 2024B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
38. NeurIPS 2024BOLD: Boolean Logic Deep Learning
39. NeurIPS 2024Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
40. NeurIPS 2024Bridging the Divide: Reconsidering Softmax and Linear Attention
41. NeurIPS 2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
42. NeurIPS 2024Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
43. NeurIPS 2024CALANet: Cheap All-Layer Aggregation for Human Activity Recognition
44. NeurIPS 2024Calibrated Self-Rewarding Vision Language Models
45. NeurIPS 2024Can neural operators always be continuously discretized?
46. NeurIPS 2024CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
47. NeurIPS 2024Cell ontology guided transcriptome foundation model
48. NeurIPS 2024Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
49. NeurIPS 2024Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
50. NeurIPS 2024Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers

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。