序列推荐论文趋势 2023–2026

主要结论

• 序列推荐论文从 2023 年的 39 篇增长到 2026 年的 43 篇，三年间扩大到约 1.1 倍。
• NeurIPS 是发序列推荐论文最多的会议，2023–2026 年共 67 篇，占四个会议总量的 47%。
• 交叉方向里涨得最快的是MCTS：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 5 篇。
• 在「推荐与广告」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的点击率预测是 2.6 倍，序列推荐是 1.1 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 2026An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation
• ICML 2026Sequential Group Composition: A Window into the Mechanics of Deep Learning
• ICLR 2026Energy-Regularized Sequential Model Editing on Hyperspheres
• CVPR 2026Online3R Online Learning for Consistent Sequential Reconstruction Based on Geometry
• NeurIPS 2025Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
• ICML 2025A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
• ICLR 2025A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation
• NeurIPS 2024CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence
• ICML 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
• ICLR 2024Parallelizing non-linear sequential models over the sequence length
• CVPR 2024MuseChat: A Conversational Music Recommendation System for Videos
• NeurIPS 2023Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments
• ICML 2023A Kernel Stein Test of Goodness of Fit for Sequential Models
• ICLR 2023Neural-based classification rule learning for sequential data
• CVPR 2023Guided Recommendation for Model Fine-Tuning
• NeurIPS 2026DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential Experiments
• ICML 2026Asymptotically Optimal Sequential Testing with Markovian Data
• ICLR 2026Sequential Parallel Duality in Prefix Scannable Models
• CVPR 2026MGDHand Multi-Granularity Prior-to-Inertial Distillation Framework for Sequential 3D Hand Pose
• NeurIPS 2025FFN Fusion: Rethinking Sequential Computation in Large Language Models

全部序列推荐论文

共 11 篇，第 1 / 1 页

1. ICML 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
2. ICML 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
3. ICML 2024On the Embedding Collapse when Scaling up Recommendation Models
4. ICML 2024On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation
5. ICML 2024Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams
6. ICML 2024Pursuing Overall Welfare in Federated Learning through Sequential Decision Making
7. ICML 2024Reducing sequential change detection to sequential estimation
8. ICML 2024Sequential Disentanglement by Extracting Static Information From A Single Sequence Element
9. ICML 2024Sequential Kernel Goodness-of-fit Testing
10. ICML 2024Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
11. ICML 2024Wukong: Towards a Scaling Law for Large-Scale Recommendation

常见问题

2023–2026 年四大会议一共有多少篇序列推荐论文？

共 142 篇，按年份分别是 2023 年 39 篇、2024 年 31 篇、2025 年 29 篇、2026 年 43 篇。

NeurIPS 2026 有多少篇序列推荐论文？

NeurIPS 2026 有 20 篇序列推荐论文，上一届是 19 篇。

ICLR 2026 有多少篇序列推荐论文？

ICLR 2026 有 10 篇序列推荐论文，上一届是 6 篇。

ICML 2026 有多少篇序列推荐论文？

ICML 2026 有 11 篇序列推荐论文，上一届是 4 篇。

CVPR 2026 有多少篇序列推荐论文？

CVPR 2026 有 2 篇序列推荐论文。

哪个会议的序列推荐论文最多？

NeurIPS，2023–2026 年共 67 篇。