交叉编码重排论文趋势 2023–2026

主要结论

• 交叉编码重排论文从 2023 年的 40 篇增长到 2026 年的 121 篇，三年间扩大到约 3.0 倍。
• CVPR 是发交叉编码重排论文最多的会议，2023–2026 年共 115 篇，占四个会议总量的 44%。
• 交叉方向里涨得最快的是三维视觉：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 11 篇。
• 在「信息检索」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的稠密检索是 2.7 倍，交叉编码重排是 3.0 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 2026A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training Data
• ICML 2026Clustered Influence Functions
• ICLR 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
• CVPR 2026Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
• NeurIPS 2025Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
• ICML 2025DeepCrossAttention: Supercharging Transformer Residual Connections
• ICLR 2025CBQ: Cross-Block Quantization for Large Language Models
• CVPR 2025A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models
• NeurIPS 2024Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias
• ICML 2024Improved Dimensionality Dependence for Zeroth-Order Optimisation over Cross-Polytopes
• ICLR 2024Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
• CVPR 2024How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?
• NeurIPS 2023Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
• ICML 2023Iterative Approximate Cross-Validation
• ICLR 2023Cross-Layer Retrospective Retrieving via Layer Attention
• CVPR 20233D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention
• NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
• ICML 2026Vector Linking via Cross-Model Local Isometric Consistency
• ICLR 2026Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation
• CVPR 2026CAR-SAM Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything

全部交叉编码重排论文

共 13 篇，第 1 / 1 页

1. ICLR 2026Align-SAM: Seeking Flatter Minima for Better Cross-Subset Alignment
2. ICLR 2026CASteer: Cross-Attention Steering for Controllable Concept Erasure
3. ICLR 2026CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally
4. ICLR 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
5. ICLR 2026Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation
6. ICLR 2026Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
7. ICLR 2026Exploring the Potential of Encoder-free Architectures in 3D LMMs
8. ICLR 2026Graphon Cross-Validation: Assessing Models on Network Data
9. ICLR 2026Proximal Diffusion Neural Sampler
10. ICLR 2026Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding
11. ICLR 2026Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
12. ICLR 2026TRIDENT: Cross-Domain Trajectory Spatio-Temporal Representation via Distance-Preserving Triplet Learning
13. ICLR 2026XIL: Cross-Expanding Incremental Learning

常见问题

2023–2026 年四大会议一共有多少篇交叉编码重排论文？

共 260 篇，按年份分别是 2023 年 40 篇、2024 年 51 篇、2025 年 48 篇、2026 年 121 篇。

NeurIPS 2026 有多少篇交叉编码重排论文？

NeurIPS 2026 有 50 篇交叉编码重排论文，上一届是 11 篇。

ICLR 2026 有多少篇交叉编码重排论文？

ICLR 2026 有 13 篇交叉编码重排论文，上一届是 7 篇。

ICML 2026 有多少篇交叉编码重排论文？

ICML 2026 有 9 篇交叉编码重排论文，上一届是 9 篇。

CVPR 2026 有多少篇交叉编码重排论文？

CVPR 2026 有 49 篇交叉编码重排论文，上一届是 21 篇。

哪个会议的交叉编码重排论文最多？

CVPR，2023–2026 年共 115 篇。