arxiv:2608.17067
Carlos Hinojosa
carlosh93
AI & ML interests
AI Safety, Privacy, Machine Learning, Computer Vision
Recent Activity
upvoted a paper 25 days ago
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces upvoted a paper 25 days ago
The Thinking Leakage in Reinforcement Learning for LLMs upvoted a paper about 1 month ago
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation