diff --git a/README.md b/README.md
index 3a3a77d..fee9599 100644
--- a/README.md
+++ b/README.md
@@ -67,6 +67,13 @@ Related Codes:
 - By topic: [doc/awesome_papers.md](/doc/awesome_paper.md)
 - By date: [doc/awesome_paper_date.md](/doc/awesome_paper_date.md)
 
+*Updated at 2024-12-25:*
+
+- Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions [[arxiv](http://arxiv.org/abs/2412.16504)]
+  - Privacy in LLM fine-tuning 
+
+- Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers [[arxiv](http://arxiv.org/abs/2412.16901)]
+  - Generate gradients for TTA 
 
 *Updated at 2024-12-19:*
 
diff --git a/doc/awesome_paper.md b/doc/awesome_paper.md
index 9bab627..5e74a9a 100644
--- a/doc/awesome_paper.md
+++ b/doc/awesome_paper.md
@@ -183,6 +183,9 @@ Here, we list some papers by topic. For list by date, please refer to [papers by
 
 ## Per-training/Finetuning
 
+- Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions [[arxiv](http://arxiv.org/abs/2412.16504)]
+  - Privacy in LLM fine-tuning 
+
 - Transfer Learning on Multi-Dimensional Data: A Novel Approach to Neural Network-Based Surrogate Modeling [[arxiv](http://arxiv.org/abs/2410.12241)]
   - Transfer learning on multi-dimensioal data
 
@@ -2023,6 +2026,9 @@ Here, we list some papers by topic. For list by date, please refer to [papers by
 
 ### Papers
 
+- Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers [[arxiv](http://arxiv.org/abs/2412.16901)]
+  - Generate gradients for TTA 
+
 - Is Large-Scale Pretraining the Secret to Good Domain Generalization? [[arxiv](https://arxiv.org/abs/2412.02856)]
   - Large-scale pre-training vs domain generalization