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 35 篇，第 1 / 1 页

1. NeurIPS 2026COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
2. NeurIPS 2026DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization
3. NeurIPS 2026LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure
4. NeurIPS 2026LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs
5. NeurIPS 2026On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
6. NeurIPS 2026Shared Truth: Emergent Truth Properties in Large Language Models via Heterogeneous Injection-based Transfer
7. NeurIPS 2026Similarity-Constrained Reweighting for Complex Query Answering on Knowledge Graphs
8. NeurIPS 2026VOID: Backdoor Injection through Knowledge Vacuity in Federated Unlearning
9. NeurIPS 2026You Don’t Need Aligned Representations: Knowledge Distillation via Random Prototype Spaces
10. NeurIPS 2025Better Language Model Inversion by Compactly Representing Next-Token Distributions
11. NeurIPS 2025Elastic Robust Unlearning of Specific Knowledge in Large Language Models
12. NeurIPS 2025From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
13. NeurIPS 2025Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning
14. NeurIPS 2025KeeA*: Epistemic Exploratory A* Search via Knowledge Calibration
15. NeurIPS 2025KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference
16. NeurIPS 2025Knowledge Distillation of Uncertainty using Deep Latent Factor Model
17. NeurIPS 2025Neural Tangent Knowledge Distillation for Optical Convolutional Networks
18. NeurIPS 2025PLD: A Choice-Theoretic List-Wise Knowledge Distillation
19. NeurIPS 2025Rethinking Residual Distribution in Locate-then-Edit Model Editing
20. NeurIPS 2025Root Cause Analysis of Outliers with Missing Structural Knowledge
21. NeurIPS 2025Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
22. NeurIPS 2024ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization
23. NeurIPS 2024Cost-efficient Knowledge-based Question Answering with Large Language Models
24. NeurIPS 2024Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
25. NeurIPS 2024FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
26. NeurIPS 2024How Do Large Language Models Acquire Factual Knowledge During Pretraining?
27. NeurIPS 2024Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
28. NeurIPS 2024Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
29. NeurIPS 2024MeMo: Meaningful, Modular Controllers via Noise Injection
30. NeurIPS 2024Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
31. NeurIPS 2024Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
32. NeurIPS 2023Deep Reinforcement Learning with Plasticity Injection
33. NeurIPS 2023Improving the Knowledge Gradient Algorithm
34. NeurIPS 2023Knowledge Distillation Performs Partial Variance Reduction
35. NeurIPS 2023Thrust: Adaptively Propels Large Language Models with External Knowledge

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。