Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models
Dongxin Guo, Jikun Wu, Siu Ming Yiu
Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial exampl…
cs.LG2026
Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension
Dongxin Guo, Jikun Wu, Siu Ming Yiu
Spiking transformers achieve competitive accuracy with conventional transformers while offering - energy efficiency on neuromorphic hardware, yet no theoretical frame…
cs.LG2026
When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth
Dongxin Guo, Jikun Wu, Siu Ming Yiu
Early-exit neural networks enable adaptive computation by allowing confident predictions to exit at intermediate layers, achieving 2-8 inference speedup. Despite widespread…