Knowledge Injection papers, 2023–2026

Key findings

• Knowledge Injection fell from 34 papers in 2023 to 26 in 2026, so interest is cooling.
• CVPR publishes the most Knowledge Injection work: 38 papers from 2023 to 2026, 29% of the four-venue total.
• The fastest-growing overlap is with Knowledge Graphs: papers tagged with both rose from 30 in 2023 to 15 in 2026.
• Among the 5 topics under Neurosymbolic AI, it ranks #5 by 2026 paper count; the fastest grower in the group, Mathematical Reasoning, is up 10x versus 0.8x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Knowledge Injection papers

32 papers, page 1 of 1

1. CVPR 2025DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification
2. CVPR 2025Knowledge Bridger: Towards Training-Free Missing Modality Completion
3. CVPR 2025Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks
4. CVPR 2025Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction
5. CVPR 2025VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
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. ICML 2025ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence
16. ICML 2025AnyEdit: Edit Any Knowledge Encoded in Language Models
17. ICML 2025Distilling the Knowledge in Data Pruning
18. ICML 2025Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
19. ICML 2025TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
20. ICML 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
21. NeurIPS 2025Better Language Model Inversion by Compactly Representing Next-Token Distributions
22. NeurIPS 2025Elastic Robust Unlearning of Specific Knowledge in Large Language Models
23. NeurIPS 2025From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
24. NeurIPS 2025Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning
25. NeurIPS 2025KeeA*: Epistemic Exploratory A* Search via Knowledge Calibration
26. NeurIPS 2025KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference
27. NeurIPS 2025Knowledge Distillation of Uncertainty using Deep Latent Factor Model
28. NeurIPS 2025Neural Tangent Knowledge Distillation for Optical Convolutional Networks
29. NeurIPS 2025PLD: A Choice-Theoretic List-Wise Knowledge Distillation
30. NeurIPS 2025Rethinking Residual Distribution in Locate-then-Edit Model Editing
31. NeurIPS 2025Root Cause Analysis of Outliers with Missing Structural Knowledge
32. NeurIPS 2025Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity

FAQ

How many Knowledge Injection papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

131 in total: 34 in 2023, 39 in 2024, 32 in 2025, 26 in 2026.

How many Knowledge Injection papers are at NeurIPS 2026?

NeurIPS 2026 has 9 Knowledge Injection papers, versus 12 the year before.

How many Knowledge Injection papers are at ICLR 2026?

ICLR 2026 has 5 Knowledge Injection papers, versus 9 the year before.

How many Knowledge Injection papers are at ICML 2026?

ICML 2026 has 4 Knowledge Injection papers, versus 6 the year before.

How many Knowledge Injection papers are at CVPR 2026?

CVPR 2026 has 8 Knowledge Injection papers, versus 5 the year before.

Which conference publishes the most Knowledge Injection papers?

CVPR, with 38 papers from 2023 to 2026.