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 536 篇，第 11 / 11 页

501. NeurIPS 2023Geometry-Aware Adaptation for Pretrained Models
502. NeurIPS 2023Global Optimality in Bivariate Gradient-based DAG Learning
503. NeurIPS 2023Grassmann Manifold Flows for Stable Shape Generation
504. NeurIPS 2023Guiding The Last Layer in Federated Learning with Pre-Trained Models
505. NeurIPS 2023Large Language Models can Implement Policy Iteration
506. NeurIPS 2023Learning Large-Scale MTP$_2$ Gaussian Graphical Models via Bridge-Block Decomposition
507. NeurIPS 2023Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
508. NeurIPS 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition
509. NeurIPS 2023Module-wise Adaptive Distillation for Multimodality Foundation Models
510. NeurIPS 2023Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine
511. NeurIPS 2023Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes
512. NeurIPS 2023On Learning Latent Models with Multi-Instance Weak Supervision
513. NeurIPS 2023Paxion: Patching Action Knowledge in Video-Language Foundation Models
514. NeurIPS 2023Quantification of Uncertainty with Adversarial Models
515. NeurIPS 2023RADAR: Robust AI-Text Detection via Adversarial Learning
516. NeurIPS 2023RanPAC: Random Projections and Pre-trained Models for Continual Learning
517. NeurIPS 2023Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests
518. NeurIPS 2023Rethinking Gauss-Newton for learning over-parameterized models
519. NeurIPS 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models
520. NeurIPS 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
521. NeurIPS 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
522. NeurIPS 2023Semantic HELM: A Human-Readable Memory for Reinforcement Learning
523. NeurIPS 2023Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
524. NeurIPS 2023SSL4EO-L: Datasets and Foundation Models for Landsat Imagery
525. NeurIPS 2023STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
526. NeurIPS 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
527. NeurIPS 2023The Learnability of In-Context Learning
528. NeurIPS 2023The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit
529. NeurIPS 2023Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification
530. NeurIPS 2023Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
531. NeurIPS 2023Towards Label-free Scene Understanding by Vision Foundation Models
532. NeurIPS 2023Unbiased learning of deep generative models with structured discrete representations
533. NeurIPS 2023VanillaNet: the Power of Minimalism in Deep Learning
534. NeurIPS 2023What Do Deep Saliency Models Learn about Visual Attention?
535. NeurIPS 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
536. NeurIPS 2023Your representations are in the network: composable and parallel adaptation for large scale models

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。