Haebin Seong's picture

4 2 1

Haebin Seong

hbseong

·

https://imnotkind.github.io/

haebin-seong-95097615a

AI & ML interests

None yet

Recent Activity

posted an update about 1 month ago

🚨🔥 HOT MODEL!! Currently 870 downloads!!! 🔥🚨 Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥 👉 Check it out: https://huggingface.co/hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡) More details in our paper: https://arxiv.org/abs/2410.01524 📜 #HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning

posted an update about 2 months ago

🚨🔥 New Release Alert! 🔥🚨 Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥 👉 Check it out: https://huggingface.co/hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡) More details in our paper: https://arxiv.org/abs/2410.01524 📜 #HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning

View all activity

Organizations

None yet

hbseong's activity

upvoted 2 papers 3 months ago

Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems

Paper • 2410.13334 • Published Oct 17, 2024 • 12

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Paper • 2410.01524 • Published Oct 2, 2024 • 3