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 209 篇，第 4 / 5 页

  1. NeurIPS 2024QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
  2. NeurIPS 2024Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices
  3. NeurIPS 2024Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
  4. NeurIPS 2024Reinforced Cross-Domain Knowledge Distillation on Time Series Data
  5. NeurIPS 2024Relating Hopfield Networks to Episodic Control
  6. NeurIPS 2024Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
  7. NeurIPS 2024Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
  8. NeurIPS 2024Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting
  9. NeurIPS 2024Rethinking Imbalance in Image Super-Resolution for Efficient Inference
  10. NeurIPS 2024Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
  11. NeurIPS 2024Retrieval & Fine-Tuning for In-Context Tabular Models
  12. NeurIPS 2024Revisiting motion information for RGB-Event tracking with MOT philosophy
  13. NeurIPS 2024Revisiting the Integration of Convolution and Attention for Vision Backbone
  14. NeurIPS 2024RMLR: Extending Multinomial Logistic Regression into General Geometries
  15. NeurIPS 2024Robustly overfitting latents for flexible neural image compression
  16. NeurIPS 2024Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
  17. NeurIPS 2024Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
  18. NeurIPS 2024S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
  19. NeurIPS 2024Scaling Law for Time Series Forecasting
  20. NeurIPS 2024Scaling White-Box Transformers for Vision
  21. NeurIPS 2024Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
  22. NeurIPS 2024Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
  23. NeurIPS 2024Selective Attention: Enhancing Transformer through Principled Context Control
  24. NeurIPS 2024Separations in the Representational Capabilities of Transformers and Recurrent Architectures
  25. NeurIPS 2024Set-based Neural Network Encoding Without Weight Tying
  26. NeurIPS 2024ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
  27. NeurIPS 2024SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
  28. NeurIPS 2024Single Image Reflection Separation via Dual-Stream Interactive Transformers
  29. NeurIPS 2024Slot State Space Models
  30. NeurIPS 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
  31. NeurIPS 2024Spectral Adapter: Fine-Tuning in Spectral Space
  32. NeurIPS 2024Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks
  33. NeurIPS 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
  34. NeurIPS 2024Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
  35. NeurIPS 2024SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
  36. NeurIPS 2024SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
  37. NeurIPS 2024The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
  38. NeurIPS 2024The Expressive Capacity of State Space Models: A Formal Language Perspective
  39. NeurIPS 2024The Mamba in the Llama: Distilling and Accelerating Hybrid Models
  40. NeurIPS 2024The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks
  41. NeurIPS 2024Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
  42. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
  43. NeurIPS 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
  44. NeurIPS 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
  45. NeurIPS 2024Towards Croppable Implicit Neural Representations
  46. NeurIPS 2024Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
  47. NeurIPS 2024Understanding and Minimising Outlier Features in Transformer Training
  48. NeurIPS 2024Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
  49. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
  50. NeurIPS 2024Understanding Transformer Reasoning Capabilities via Graph Algorithms

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