5 papers
SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
Mayur Akewar, Ravi Ranjan
Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before re…
CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs
Ravi Ranjan, Utkarsh Grover, Mayur Akewar +2
Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods…
WSBD: Freezing-Based Optimizer for Quantum Neural Networks
Christopher Kverne, Mayur Akewar, Yuqian Huo +2
The training of Quantum Neural Networks (QNNs) is hindered by the high computational cost of gradient estimation and the barren plateau problem, where optimization landscapes becom…
KORAL: Knowledge Graph Guided LLM Reasoning for SSD Operational Analysis
Mayur Akewar, Sandeep Madireddy, Dongsheng Luo +1
Solid State Drives (SSDs) are critical to datacenters, consumer platforms, and mission-critical systems. Yet diagnosing their performance and reliability is difficult because data…
Revisiting Noise-adaptive Transpilation in Quantum Computing: How Much Impact Does it Have?
Yuqian Huo, Jinbiao Wei, Christopher Kverne +3
Transpilation, particularly noise-aware optimization, is widely regarded as essential for maximizing the performance of quantum circuits on superconducting quantum computers. The c…