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 1 month ago
ToxReason: A Benchmark for Mechanistic Chemical Toxicity Reasoning via Adverse Outcome Pathway upvoted a paper about 1 month ago
Learning from Negative Samples in Generative Biomedical Entity Linking upvoted a paper about 2 months ago
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack