arxiv:2505.20139
Lipeng (Tony) He
ttttonyhe
AI & ML interests
Trustworthy Machine Learning
Recent Activity
authored
a paper
10 days ago
StructEval: Benchmarking LLMs' Capabilities to Generate Structural
Outputs
liked
a Space
3 months ago
Xenova/the-tokenizer-playground
commented on
a paper
4 months ago
Activation Approximations Can Incur Safety Vulnerabilities Even in
Aligned LLMs: Comprehensive Analysis and Defense
Organizations
