表格深度学习论文趋势 2023–2026

主要结论

• 表格深度学习论文从 2023 年的 150 篇降到 2026 年的 33 篇，热度在回落。
• NeurIPS 是发表格深度学习论文最多的会议，2023–2026 年共 133 篇，占四个会议总量的 62%。
• 交叉方向里涨得最快的是驾驶仿真：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 6 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的时间序列是 3.2 倍，表格深度学习是 0.2 倍。

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

• NeurIPS 2026Coherent Routing in Decision Trees: Phase-Interference Learning for Interpretable Tabular Prediction
• ICML 2026Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
• ICLR 2026Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
• CVPR 2026MultiModalPFN Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
• NeurIPS 2025ConTextTab: A Semantics-Aware Tabular In-Context Learner
• ICML 2025Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data
• ICLR 2025Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later
• NeurIPS 2024WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata
• ICML 2024BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model
• ICLR 2024GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data
• NeurIPS 2023Accurate Interpolation for Scattered Data through Hierarchical Residual Refinement
• ICML 2023Compressing Tabular Data via Latent Variable Estimation
• ICLR 2023TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing
• NeurIPS 2026LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning
• ICML 2026FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
• NeurIPS 2025Feature-aware Modulation for Learning from Temporal Tabular Data
• ICML 2025TabFlex: Scaling Tabular Learning to Millions with Linear Attention
• ICLR 2025SAVA: Scalable Learning-Agnostic Data Valuation
• NeurIPS 2024Evaluating language models as risk scores
• ICML 2024Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images

全部表格深度学习论文

共 63 篇，第 1 / 2 页

1. ICML 2026Attacks on Machine-Text Detectors Retain Stylistic Fingerprints
2. ICML 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
3. ICML 2026Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
4. ICML 2026FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
5. ICML 2026Float8@2bits: Entropy Coding Enables Data-Free Model Compression
6. ICML 2026GraphPFN: A Prior-Data Fitted Graph Foundation Model
7. ICML 2026HInT: Hypergraph Infusion at the Structural Layers Improves Table Understanding
8. ICML 2026Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
9. ICML 2026LassoFlexNet: a Flexible Neural Architecture for Tabular Data
10. ICML 2026OMP: One-step Meanflow Policy with Directional Alignment
11. ICML 2026On the Fragility of Data Attribution When Learning Is Distributed
12. ICML 2026pTNAS: Progressive Neural Architecture Search for Tabular Data
13. ICML 2026Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining
14. ICML 2026TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning
15. ICML 2026TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
16. ICML 2026TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
17. ICML 2026The Data Manifold under the Microscope
18. ICML 2026TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
19. ICML 2026Towards Efficient LLMs Annealing with Principled Sample Selection
20. ICML 2026TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
21. ICML 2026Tuning-Free One-Class Discriminant Learning for Tabular Anomaly Detection
22. ICML 2026Unveiling the Role of Data Uncertainty in Tabular Deep Learning
23. ICML 2025Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data
24. ICML 2025TabFlex: Scaling Tabular Learning to Millions with Linear Attention
25. ICML 2025Understanding the Limits of Deep Tabular Methods with Temporal Shift
26. ICML 2024Beyond Individual Input for Deep Anomaly Detection on Tabular Data
27. ICML 2024BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model
28. ICML 2024Interpretable Deep Clustering for Tabular Data
29. ICML 2024InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation
30. ICML 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
31. ICML 2024Position: Why Tabular Foundation Models Should Be a Research Priority
32. ICML 2024ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
33. ICML 2024SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP
34. ICML 2024Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images
35. ICML 2023Adversarial Collaborative Learning on Non-IID Features
36. ICML 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting
37. ICML 2023Causal Structure Learning for Latent Intervened Non-stationary Data
38. ICML 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis
39. ICML 2023Compressing Tabular Data via Latent Variable Estimation
40. ICML 2023Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
41. ICML 2023Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach
42. ICML 2023Do Machine Learning Models Learn Statistical Rules Inferred from Data?
43. ICML 2023FeDXL: Provable Federated Learning for Deep X-Risk Optimization
44. ICML 2023Learning Belief Representations for Partially Observable Deep RL
45. ICML 2023Learning Globally Smooth Functions on Manifolds
46. ICML 2023Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator
47. ICML 2023MODeL: Memory Optimizations for Deep Learning
48. ICML 2023Nearly-tight Bounds for Deep Kernel Learning
49. ICML 2023On Generalizations of Some Distance Based Classifiers for HDLSS Data
50. ICML 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learning

常见问题

2023–2026 年四大会议一共有多少篇表格深度学习论文？

共 214 篇，按年份分别是 2023 年 150 篇、2024 年 17 篇、2025 年 14 篇、2026 年 33 篇。

NeurIPS 2026 有多少篇表格深度学习论文？

NeurIPS 2026 有 9 篇表格深度学习论文，上一届是 5 篇。

ICLR 2026 有多少篇表格深度学习论文？

ICLR 2026 有 1 篇表格深度学习论文，上一届是 6 篇。

ICML 2026 有多少篇表格深度学习论文？

ICML 2026 有 22 篇表格深度学习论文，上一届是 3 篇。

CVPR 2026 有多少篇表格深度学习论文？

CVPR 2026 有 1 篇表格深度学习论文。

哪个会议的表格深度学习论文最多？

NeurIPS，2023–2026 年共 133 篇。