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 53 篇，第 1 / 2 页

1. ICML 2025Are Large Brainwave Foundation Models Capable Yet ? Insights from Fine-Tuning
2. ICML 2025BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
3. ICML 2025Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
4. ICML 2025Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions
5. ICML 2025Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
6. ICML 2025Contextures: Representations from Contexts
7. ICML 2025Contrastive Localized Language-Image Pre-Training
8. ICML 2025Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development
9. ICML 2025Diffusion Instruction Tuning
10. ICML 2025ExLM: Rethinking the Impact of $\texttt{[MASK]}$ Tokens in Masked Language Models
11. ICML 2025Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
12. ICML 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
13. ICML 2025FG-CLIP: Fine-Grained Visual and Textual Alignment
14. ICML 2025From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
15. ICML 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
16. ICML 2025GraphGPT: Generative Pre-trained Graph Eulerian Transformer
17. ICML 2025Griffin: Towards a Graph-Centric Relational Database Foundation Model
18. ICML 2025How Expressive are Knowledge Graph Foundation Models?
19. ICML 2025How Far Is Video Generation from World Model: A Physical Law Perspective
20. ICML 2025Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
21. ICML 2025In-Context Deep Learning via Transformer Models
22. ICML 2025In-Context Learning as Conditioned Associative Memory Retrieval
23. ICML 2025Large Continual Instruction Assistant
24. ICML 2025Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
25. ICML 2025Learning to (Learn at Test Time): RNNs with Expressive Hidden States
26. ICML 2025LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
27. ICML 2025M+: Extending MemoryLLM with Scalable Long-Term Memory
28. ICML 2025Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
29. ICML 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
30. ICML 2025MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
31. ICML 2025On Path to Multimodal Generalist: General-Level and General-Bench
32. ICML 2025Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
33. ICML 2025Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
34. ICML 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
35. ICML 2025Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
36. ICML 2025Primitive Vision: Improving Diagram Understanding in MLLMs
37. ICML 2025QMamba: On First Exploration of Vision Mamba for Image Quality Assessment
38. ICML 2025Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems
39. ICML 2025Rethinking the Bias of Foundation Model under Long-tailed Distribution
40. ICML 2025Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
41. ICML 2025Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
42. ICML 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
43. ICML 2025Sundial: A Family of Highly Capable Time Series Foundation Models
44. ICML 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
45. ICML 2025The Double-Ellipsoid Geometry of CLIP
46. ICML 2025The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
47. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
48. ICML 2025Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
49. ICML 2025Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
50. ICML 2025What Has a Foundation Model Found? Inductive Bias Reveals World 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。