知识注入论文趋势 2023–2026

主要结论

• 知识注入论文从 2023 年的 34 篇降到 2026 年的 26 篇，热度在回落。
• CVPR 是发知识注入论文最多的会议，2023–2026 年共 38 篇，占四个会议总量的 29%。
• 交叉方向里涨得最快的是知识图谱：同时属于两个主题的论文从 2023 年的 30 篇增至 2026 年的 15 篇。
• 在「神经符号」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的数学推理是 10 倍，知识注入是 0.8 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 2026DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization
• ICML 2026SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
• ICLR 2026NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection
• CVPR 2026Distilling Balanced Knowledge from a Biased Teacher
• NeurIPS 2025From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
• ICML 2025TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
• ICLR 2025How new data permeates LLM knowledge and how to dilute it
• CVPR 2025DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification
• NeurIPS 2024FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
• ICML 2024Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation
• ICLR 2024DistillSpec: Improving Speculative Decoding via Knowledge Distillation
• CVPR 2024Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
• NeurIPS 2023Improving the Knowledge Gradient Algorithm
• ICML 2023Large Language Models Struggle to Learn Long-Tail Knowledge
• ICLR 2023Noise Injection Node Regularization for Robust Learning
• CVPR 2023AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
• NeurIPS 2026Shared Truth: Emergent Truth Properties in Large Language Models via Heterogeneous Injection-based Transfer
• ICML 2026RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
• ICLR 2026Knowledge Distillation as Decontamination? Revisiting the “Data Laundering” Concern
• CVPR 2026Dynamic Magic Unleashing Restricted Knowledge for Lifelong Person Re-Identification

全部知识注入论文

共 30 篇，第 1 / 1 页

1. ICLR 2026AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
2. ICLR 2026Inheriting Generalizable Knowledge from LLMs to Diverse Vertical Tasks
3. ICLR 2026Knowledge Distillation as Decontamination? Revisiting the “Data Laundering” Concern
4. ICLR 2026NDAD: Negative-Direction Aware Decoding for Large Language Models via Controllable Hallucination Signal Injection
5. ICLR 2026When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations
6. ICLR 2025Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?
7. ICLR 2025Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
8. ICLR 2025ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains
9. ICLR 2025Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
10. ICLR 2025How new data permeates LLM knowledge and how to dilute it
11. ICLR 2025KBLaM: Knowledge Base augmented Language Model
12. ICLR 2025Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
13. ICLR 2025Large Scale Knowledge Washing
14. ICLR 2025Self-Updatable Large Language Models by Integrating Context into Model Parameters
15. ICLR 2024A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
16. ICLR 2024DistillSpec: Improving Speculative Decoding via Knowledge Distillation
17. ICLR 2024GeoLLM: Extracting Geospatial Knowledge from Large Language Models
18. ICLR 2024MiniLLM: Knowledge Distillation of Large Language Models
19. ICLR 2024Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
20. ICLR 2024Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
21. ICLR 2023Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation
22. ICLR 2023Dataless Knowledge Fusion by Merging Weights of Language Models
23. ICLR 2023Function-Consistent Feature Distillation
24. ICLR 2023Gradient Boosting Performs Gaussian Process Inference
25. ICLR 2023Interpretable Geometric Deep Learning via Learnable Randomness Injection
26. ICLR 2023Noise Injection Node Regularization for Robust Learning
27. ICLR 2023NORM: Knowledge Distillation via N-to-One Representation Matching
28. ICLR 2023Scaffolding a Student to Instill Knowledge
29. ICLR 2023simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
30. ICLR 2023TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs

常见问题

2023–2026 年四大会议一共有多少篇知识注入论文？

共 131 篇，按年份分别是 2023 年 34 篇、2024 年 39 篇、2025 年 32 篇、2026 年 26 篇。

NeurIPS 2026 有多少篇知识注入论文？

NeurIPS 2026 有 9 篇知识注入论文，上一届是 12 篇。

ICLR 2026 有多少篇知识注入论文？

ICLR 2026 有 5 篇知识注入论文，上一届是 9 篇。

ICML 2026 有多少篇知识注入论文？

ICML 2026 有 4 篇知识注入论文，上一届是 6 篇。

CVPR 2026 有多少篇知识注入论文？

CVPR 2026 有 8 篇知识注入论文，上一届是 5 篇。

哪个会议的知识注入论文最多？

CVPR，2023–2026 年共 38 篇。