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 192 篇，第 3 / 4 页

  1. NeurIPS 2024MatFormer: Nested Transformer for Elastic Inference
  2. NeurIPS 2024MatrixNet: Learning over symmetry groups using learned group representations
  3. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
  4. NeurIPS 2024MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
  5. NeurIPS 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
  6. NeurIPS 2024Meta-Learning Universal Priors Using Non-Injective Change of Variables
  7. NeurIPS 2024MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
  8. NeurIPS 2024Mixtures of Experts for Audio-Visual Learning
  9. NeurIPS 2024MoEUT: Mixture-of-Experts Universal Transformers
  10. NeurIPS 2024MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
  11. NeurIPS 2024Monomial Matrix Group Equivariant Neural Functional Networks
  12. NeurIPS 2024MoVA: Adapting Mixture of Vision Experts to Multimodal Context
  13. NeurIPS 2024Multi-Head Mixture-of-Experts
  14. NeurIPS 2024Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
  15. NeurIPS 2024Neural Experts: Mixture of Experts for Implicit Neural Representations
  16. NeurIPS 2024NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
  17. NeurIPS 2024On Feature Learning in Structured State Space Models
  18. NeurIPS 2024On Sampling Strategies for Spectral Model Sharding
  19. NeurIPS 2024Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
  20. NeurIPS 2024Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
  21. NeurIPS 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Length
  22. NeurIPS 2024Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective
  23. NeurIPS 2024Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
  24. NeurIPS 2024Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
  25. NeurIPS 2024PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
  26. NeurIPS 2024PointMamba: A Simple State Space Model for Point Cloud Analysis
  27. NeurIPS 2024Poseidon: Efficient Foundation Models for PDEs
  28. NeurIPS 2024PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
  29. NeurIPS 2024Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
  30. NeurIPS 2024ProxyFusion: Face Feature Aggregation Through Sparse Experts
  31. NeurIPS 2024Q-VLM: Post-training Quantization for Large Vision-Language Models
  32. NeurIPS 2024QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
  33. NeurIPS 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
  34. NeurIPS 2024QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
  35. NeurIPS 2024Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices
  36. NeurIPS 2024Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
  37. NeurIPS 2024Reinforced Cross-Domain Knowledge Distillation on Time Series Data
  38. NeurIPS 2024Relating Hopfield Networks to Episodic Control
  39. NeurIPS 2024Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
  40. NeurIPS 2024Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
  41. NeurIPS 2024Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting
  42. NeurIPS 2024Rethinking Imbalance in Image Super-Resolution for Efficient Inference
  43. NeurIPS 2024Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
  44. NeurIPS 2024Retrieval & Fine-Tuning for In-Context Tabular Models
  45. NeurIPS 2024Revisiting motion information for RGB-Event tracking with MOT philosophy
  46. NeurIPS 2024Revisiting the Integration of Convolution and Attention for Vision Backbone
  47. NeurIPS 2024RMLR: Extending Multinomial Logistic Regression into General Geometries
  48. NeurIPS 2024Robustly overfitting latents for flexible neural image compression
  49. NeurIPS 2024Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
  50. NeurIPS 2024Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts

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