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 1 / 6 页

1. NeurIPS 2026A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
2. NeurIPS 2026AmbientFM: A Foundation Model for Ambient Sensing
3. NeurIPS 2026CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
4. NeurIPS 2026DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models
5. NeurIPS 2026Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
6. NeurIPS 2026Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees
7. NeurIPS 2026Evaluating Uncertainty Calibration in Probabilistic Time Series Foundation Models
8. NeurIPS 2026Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
9. NeurIPS 2026FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody Screening
10. NeurIPS 2026Glob3R: Global Structure-from-Motion with 3D Foundation Models
11. NeurIPS 2026GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
12. NeurIPS 2026HandXFM: Semantic-Structural Distillation for Hand Radiograph Foundation Models
13. NeurIPS 2026Inertia-1: An Open Exploration of Wearable Motion Foundation Models
14. NeurIPS 2026Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
15. NeurIPS 2026Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
16. NeurIPS 2026Multimodal Foundation Agents Should Use Brain Data as Privileged Supervision
17. NeurIPS 2026NeuroNTP - A Generalizable Multimodal Foundation Model for Epilepsy
18. NeurIPS 2026No One Knows the State-of-the-Art in Geospatial Foundation Models
19. NeurIPS 2026OpenMHC: Accelerating the Science of Wearable Foundation Models
20. NeurIPS 2026Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
21. NeurIPS 2026ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models
22. NeurIPS 2026SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception
23. NeurIPS 2026Tabular Foundation Model for Generative Modelling
24. NeurIPS 2026Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence
25. NeurIPS 2026What DNA Foundation Models Learn Beyond Sequence Composition
26. NeurIPS 2026What do EEG Foundation Models Capture from Human Brain Signals?
27. NeurIPS 2026When to Trust a PFN: Detecting Harmful Shift in Tabular Foundation Models
28. NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation Models
29. NeurIPS 2025Axial Neural Networks for Dimension-Free Foundation Models
30. NeurIPS 2025BlockScan: Detecting Anomalies in Blockchain Transactions
31. NeurIPS 2025ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data
32. NeurIPS 2025CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding
33. NeurIPS 2025Demystifying Network Foundation Models
34. NeurIPS 2025EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network
35. NeurIPS 2025Fourier Analysis Network
36. NeurIPS 2025Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis
37. NeurIPS 2025JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model
38. NeurIPS 2025Learning to Factorize Spatio-Temporal Foundation Models
39. NeurIPS 2025Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
40. NeurIPS 2025Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
41. NeurIPS 2025NeurIPT: Foundation Model for Neural Interfaces
42. NeurIPS 2025UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces
43. NeurIPS 2024$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
44. NeurIPS 2024$C^2M^3$: Cycle-Consistent Multi-Model Merging
45. NeurIPS 20243-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
46. NeurIPS 2024A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
47. NeurIPS 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecture
48. NeurIPS 2024Accelerating Transformers with Spectrum-Preserving Token Merging
49. NeurIPS 2024Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
50. NeurIPS 2024AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer

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。