9 papers
Memory Reward Inflation in Self-Improving LLM Agents
Mohammad Asadolahi, Amir Amini, Samira Talebi +2
Self-improving LLM agents increasingly learn from experience without updating any weights. Each episode is stored in an external memory, scored, and retrieved for similar future ta…
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…
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…
TA-RNN-Medical-Hybrid: A Time-Aware and Interpretable Framework for Mortality Risk Prediction
Zahra Jafari, Azadeh Zamanifar, Amirfarhad Farhadi
Accurate and interpretable mortality risk prediction in intensive care units (ICUs) remains a critical challenge due to the irregular temporal structure of electronic health record…
Deep Reinforcement Learning for Optimizing Energy Consumption in Smart Grid Systems
Abeer Alsheikhi, Amirfarhad Farhadi, Azadeh Zamanifar
The energy management problem in the context of smart grids is inherently complex due to the interdependencies among diverse system components. Although Reinforcement Learning (RL)…
TinyGuard:A lightweight Byzantine Defense for Resource-Constrained Federated Learning via Statistical Update Fingerprints
Ali Mahdavi, Santa Aghapour, Azadeh Zamanifar +1
Existing Byzantine robust aggregation mechanisms typically rely on fulldimensional gradi ent comparisons or pairwise distance computations, resulting in computational overhead that…