Haebin Seong PRO

hbseong's activity

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

upvoted a paper 9 days ago

The Last Harness You'll Ever Build

Paper • 2604.21003 • Published 17 days ago • 3

upvoted a paper 7 months ago

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Paper • 2510.05684 • Published Oct 7, 2025 • 146

upvoted a paper about 1 year ago

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

Paper • 2502.12464 • Published Feb 18, 2025 • 28

upvoted 2 papers over 1 year 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