HaoranLiu

HaoranLiu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 17 days ago

AgentDoG1.5

Collection

A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security • 11 items • Updated 4 days ago • 13

liked 2 datasets 21 days ago

thu-coai/Syncred-Bench

Viewer • Updated 18 days ago • 2.1k • 126 • 2

yangjunxiao2021/Syncred-Bench

Updated 22 days ago • 57 • 2

updated a model 23 days ago

HaoranLiu/kaggle_grpo_step100

4B • Updated 23 days ago • 13

published a model 23 days ago

HaoranLiu/kaggle_grpo_step100

4B • Updated 23 days ago • 13

updated a model 24 days ago

HaoranLiu/kaggle_grpo_step40

4B • Updated 24 days ago • 22

published a model 24 days ago

HaoranLiu/kaggle_grpo_step40

4B • Updated 24 days ago • 22

upvoted a paper 27 days ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Paper • 2605.29801 • Published 28 days ago • 144

upvoted a paper 2 months ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

Paper • 2604.12710 • Published Apr 13 • 5

upvoted 3 papers about 1 year ago

Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!

Paper • 2505.15656 • Published May 21, 2025 • 15

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study

Paper • 2505.15404 • Published May 21, 2025 • 13

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

Paper • 2505.13529 • Published May 18, 2025 • 12