Author

Bruce Changlong Xu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

Per-Channel Reduction (PCR) is proposed, a diagnostic that classifies each model into one of three mechanistic failure modes: outlier-crushes-safety, where safety lives in non-outlier channels collaterally damaged by outlier-driven scale factors; outlier-as-safety, where safety overlaps outlier channels and finer granu...

Bruce Changlong Xu, Adarsh Kumarappan, Mu Zhou · arXiv.org · 7 citations

#artificial intelligence Preprint Mar 2023

Typhoon: Gradient-Based Task-Specific Masking for Masked Language Models

Typhoon, a masking strategy that uses the gradient of the MLM loss with respect to one-hot token inputs to estimate online how much each token type contributes to the objective, is introduced and evaluated against random masking and whole-word masking.

Bruce Changlong Xu, Muhammed Shahir Abdurrahman, Hashem Elezabi · 0 citations