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 28 篇，第 1 / 1 页

1. ICML 2026From Teacher Pathways to Invariant Manifolds: Consensus Subspace Distillation for TSFMs
2. ICML 2026KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
3. ICML 2026RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
4. ICML 2026SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
5. ICML 2025ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence
6. ICML 2025AnyEdit: Edit Any Knowledge Encoded in Language Models
7. ICML 2025Distilling the Knowledge in Data Pruning
8. ICML 2025Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
9. ICML 2025TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
10. ICML 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
11. ICML 2024Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification
12. ICML 2024CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback
13. ICML 2024Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
14. ICML 2024Do Topological Characteristics Help in Knowledge Distillation?
15. ICML 2024Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation
16. ICML 2024Knowledge Distillation with Auxiliary Variable
17. ICML 2024Knowledge Graphs Can be Learned with Just Intersection Features
18. ICML 2024Layerwise Change of Knowledge in Neural Networks
19. ICML 2024Neighboring Perturbations of Knowledge Editing on Large Language Models
20. ICML 2024OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification
21. ICML 2024Revisit the Essence of Distilling Knowledge through Calibration
22. ICML 2024WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
23. ICML 2023Integrating Prior Knowledge in Contrastive Learning with Kernel
24. ICML 2023Knowledge Hypergraph Embedding Meets Relational Algebra
25. ICML 2023Large Language Models Struggle to Learn Long-Tail Knowledge
26. ICML 2023Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs
27. ICML 2023Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
28. ICML 2023Who Needs to Know? Minimal Knowledge for Optimal Coordination

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。