徐伯阳
biangbiang888
·
AI & ML interests
offline rl, interpretability, jailbreaks, alignment, sycophancy
Recent Activity
upvoted a paper about 17 hours ago
SuperNav: An Agentic Navigation System for Any Task in Any Scene liked a model 2 days ago
markush1/jailbreakDetector-v6 upvoted a paper 2 days ago
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill LifecyclesOrganizations
None yet