arxiv:2512.14629
Xin Xu
XinXuNLPer
AI & ML interests
Mechanistic Interpretability of Trustworthy LLMs and Music LLMs
Recent Activity
upvoted a paper about 1 hour ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? upvoted a paper 5 days ago
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use authored a paper 5 days ago
Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing SystemsOrganizations
