徐伯阳
biangbiang888
·
AI & ML interests
AI alignment, jailbreak detection, red teaming, model robustness, safety evaluation
Recent Activity
upvoted a paper about 12 hours ago
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents upvoted a paper about 12 hours ago
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation upvoted a paper about 12 hours ago
StudentSim: Training LLM-based Student SimulatorsOrganizations
None yet