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 536 篇，第 9 / 11 页

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

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