arxiv:2512.14629
Xin Xu
XinXuNLPer
AI & ML interests
Mechanistic Interpretability of Trustworthy LLMs and Music LLMs
Recent Activity
upvoted a paper 2 days ago
Cortex: Consolidating Context into Parametric Memory upvoted a paper about 2 months ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? upvoted a paper about 2 months ago
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory UseOrganizations
