A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework.
Data Mining and Information Systems Lab
dmis-lab
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack upvoted a paper 4 months ago
The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models upvoted a paper 7 months ago
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During
Post Training