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 3 / 5 页

  1. NeurIPS 2024Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
  2. NeurIPS 2024Is Multiple Object Tracking a Matter of Specialization?
  3. NeurIPS 2024Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
  4. NeurIPS 2024L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer
  5. NeurIPS 2024LaSCal: Label-Shift Calibration without target labels
  6. NeurIPS 2024Latent Functional Maps: a spectral framework for representation alignment
  7. NeurIPS 2024Learning diverse causally emergent representations from time series data
  8. NeurIPS 2024Learning from Highly Sparse Spatio-temporal Data
  9. NeurIPS 2024Learning Group Actions on Latent Representations
  10. NeurIPS 2024Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
  11. NeurIPS 2024Learning symmetries via weight-sharing with doubly stochastic tensors
  12. NeurIPS 2024Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
  13. NeurIPS 2024Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
  14. NeurIPS 2024LinNet: Linear Network for Efficient Point Cloud Representation Learning
  15. NeurIPS 2024LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
  16. NeurIPS 2024MambaTree: Tree Topology is All You Need in State Space Model
  17. NeurIPS 2024Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
  18. NeurIPS 2024MatFormer: Nested Transformer for Elastic Inference
  19. NeurIPS 2024MatrixNet: Learning over symmetry groups using learned group representations
  20. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
  21. NeurIPS 2024MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
  22. NeurIPS 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
  23. NeurIPS 2024Meta-Learning Universal Priors Using Non-Injective Change of Variables
  24. NeurIPS 2024MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
  25. NeurIPS 2024Mixtures of Experts for Audio-Visual Learning
  26. NeurIPS 2024MoEUT: Mixture-of-Experts Universal Transformers
  27. NeurIPS 2024MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
  28. NeurIPS 2024Monomial Matrix Group Equivariant Neural Functional Networks
  29. NeurIPS 2024MoVA: Adapting Mixture of Vision Experts to Multimodal Context
  30. NeurIPS 2024Multi-Head Mixture-of-Experts
  31. NeurIPS 2024Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
  32. NeurIPS 2024Neural Experts: Mixture of Experts for Implicit Neural Representations
  33. NeurIPS 2024NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
  34. NeurIPS 2024On Feature Learning in Structured State Space Models
  35. NeurIPS 2024On Sampling Strategies for Spectral Model Sharding
  36. NeurIPS 2024Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
  37. NeurIPS 2024Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
  38. NeurIPS 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Length
  39. NeurIPS 2024Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective
  40. NeurIPS 2024Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
  41. NeurIPS 2024Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
  42. NeurIPS 2024PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
  43. NeurIPS 2024PointMamba: A Simple State Space Model for Point Cloud Analysis
  44. NeurIPS 2024Poseidon: Efficient Foundation Models for PDEs
  45. NeurIPS 2024PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
  46. NeurIPS 2024Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
  47. NeurIPS 2024ProxyFusion: Face Feature Aggregation Through Sparse Experts
  48. NeurIPS 2024Q-VLM: Post-training Quantization for Large Vision-Language Models
  49. NeurIPS 2024QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
  50. NeurIPS 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

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