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

ICML/NeurIPS 深度学习方向：foundation_models

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 536 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

深度学习 · foundation models论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20236507072
20241920116209
202515653478
20262781357177

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

全部深度学习 · foundation models论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 206 篇，第 4 / 5 页

  1. ICML 2025GraphGPT: Generative Pre-trained Graph Eulerian Transformer
  2. ICML 2025Griffin: Towards a Graph-Centric Relational Database Foundation Model
  3. ICML 2025How Expressive are Knowledge Graph Foundation Models?
  4. ICML 2025How Far Is Video Generation from World Model: A Physical Law Perspective
  5. ICML 2025Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
  6. ICML 2025In-Context Deep Learning via Transformer Models
  7. ICML 2025In-Context Learning as Conditioned Associative Memory Retrieval
  8. ICML 2025Large Continual Instruction Assistant
  9. ICML 2025Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
  10. ICML 2025Learning to (Learn at Test Time): RNNs with Expressive Hidden States
  11. ICML 2025LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
  12. ICML 2025M+: Extending MemoryLLM with Scalable Long-Term Memory
  13. ICML 2025Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
  14. ICML 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
  15. ICML 2025MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
  16. ICML 2025On Path to Multimodal Generalist: General-Level and General-Bench
  17. ICML 2025Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
  18. ICML 2025Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
  19. ICML 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
  20. ICML 2025Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
  21. ICML 2025Primitive Vision: Improving Diagram Understanding in MLLMs
  22. ICML 2025QMamba: On First Exploration of Vision Mamba for Image Quality Assessment
  23. ICML 2025Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems
  24. ICML 2025Rethinking the Bias of Foundation Model under Long-tailed Distribution
  25. ICML 2025Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
  26. ICML 2025Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
  27. ICML 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
  28. ICML 2025Sundial: A Family of Highly Capable Time Series Foundation Models
  29. ICML 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
  30. ICML 2025The Double-Ellipsoid Geometry of CLIP
  31. ICML 2025The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
  32. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
  33. ICML 2025Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
  34. ICML 2025Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
  35. ICML 2025What Has a Foundation Model Found? Inductive Bias Reveals World Models
  36. ICML 2025What If We Recaption Billions of Web Images with LLaMA-3?
  37. ICML 2025Whitened CLIP as a Likelihood Surrogate of Images and Captions
  38. ICML 2025WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
  39. ICML 2024Asymmetry in Low-Rank Adapters of Foundation Models
  40. ICML 2024Differentially Private Bias-Term Fine-tuning of Foundation Models
  41. ICML 2024Foundation Policies with Hilbert Representations
  42. ICML 2024Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
  43. ICML 2024MOMENT: A Family of Open Time-series Foundation Models
  44. ICML 2024Position: On the Societal Impact of Open Foundation Models
  45. ICML 2024Position: Why Tabular Foundation Models Should Be a Research Priority
  46. ICML 2024Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
  47. ICML 2024Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
  48. ICML 2024To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO
  49. ICML 2024Transferring Knowledge From Large Foundation Models to Small Downstream Models
  50. ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查深度学习 · foundation models在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dl-foundation-models"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「深度学习」下的其他主题