2 papers
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…
cs.LG2026
Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions
Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi +1
Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. W…