Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
RAPID: Reliability-Aware Pair Importance Distillation
Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi +1
Inter example relational distillation transfers a teacher's representation geometry by matching relations among examples within a mini batch. Computing all pairs has quadratic comp…
cs.AI2026
Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing
Ali Mahdavi, Azaseh Zamanifar, Amirfarhad Farhadi +1
Long-prompt inference remains expensive because prefill attention scales quadratically with sequence length. We propose Spectral-LSH, a training-free prompt compression method that…