We present MARCO (Multi-Agent Reinforcement learning with Conformal Optimization), a hardware-aware neural architecture search (NAS) framework for resource-constrained edge devices. MARCO combines multi-agent reinforcement learning (MARL) with Conformal Prediction (CP) to efficiently explore architectures under strict memory and latency budgets. Unlike once-for-all (OFA) supernets that require expensive pretraining, MARCO separates the NAS task into a Hardware Configuration Agent and a Quantization Agent, coordinated via a centralized-critic, decentralized-execution (CTDE) paradigm. A calibrated CP surrogate model offers distribution-free guarantees to filter low-reward candidates before costly training or simulation, significantly accelerating the search. Experiments on MNIST, CIFAR-10, and CIFAR-100 show MARCO achieves $3-4 \times$ faster search than OFA while maintaining accuracy within 0.3% and reducing latency. Validation on the MAX78000 confirms simulator fidelity with less than 5% error.

We present FAIR-SIGHT, a post-hoc framework that enforces statistical fairness in computer vision models without retraining or access to internal parameters. The method computes a fairness-aware non-conformity score combining prediction error and demographic disparity and uses conformal prediction to calibrate a threshold that guarantees a user-specified violation rate under finite-sample, distribution-free conditions. Inputs exceeding this threshold are automatically repaired through lightweight adjustments (such as logit shifts for classification or confidence scaling for detection) to reduce group disparities while preserving accuracy. Experiments on CelebA, UTKFace, GeoDE, and COCO show over 30% reductions in DPD/EOD and detection gaps with negligible utility loss and only ∼0.5ms/img overhead, establishing FAIR-SIGHT as a practical, scalable solution for bias mitigation in black-box vision systems.

This paper introduces a novel Dynamic Co-Optimization Compiler (DCOC), which employs an adaptive Multi-Agent Reinforcement Learning (MARL) framework to enhance the efficiency of mapping machine learning (ML) models, particularly Deep Neural Networks (DNNs), onto diverse hardware platforms. DCOC incorporates three specialized actor-critic agents within MARL, each dedicated to different optimization facets: one for hardware and two for software. This cooperative strategy results in an integrated hardware/software co-optimization approach, improving the precision and speed of DNN deployments. By focusing on high-confidence configurations, DCOC effectively reduces the search space, achieving remarkable performance over existing methods. Our results demonstrate that DCOC enhances throughput by up to 37.95% while reducing optimization time by up to 42.2% across various DNN models, outperforming current state-of-the-art frameworks.

We propose FACTER, a fairness-aware framework for LLM-based recommendation systems that integrates conformal prediction with dynamic prompt engineering. By introducing an adaptive semantic variance threshold and a violation-triggered mechanism, FACTER automatically tightens fairness constraints whenever biased patterns emerge. We further develop an adversarial prompt generator that leverages historical violations to reduce repeated demographic biases without retraining the LLM. Empirical results on MovieLens and Amazon show that FACTER substantially reduces fairness violations (up to 95.5%) while maintaining strong recommendation accuracy, revealing semantic variance as a potent proxy of bias.

Ensuring fairness is essential for ethical decision-making in various domains. Informally, a neural network is considered fair if and only if it treats similar individuals similarly in a given task. We introduce FaVeR (Fairness Verification and Repair), a framework for efficiently verifying and repairing pre-trained neural networks with respect to individual fairness properties. FaVeR ensures fairness via iterative search of high-sensitivity neurons and backward adjustment of their weights, guided by counterexamples generated from fairness verification using satisfiability modulo convex programming. By addressing fairness at the neuron level, FaVeR minimizes the impact of neural network repair on the overall performance. Experimental evaluations on common fairness datasets show that FaVeR achieves a 100% fairness repair rate across all models, with accuracy reduction of less than 2.27%. Moreover, its significantly lower average runtime makes it suitable for practical applications.

This paper introduces NeuroBlend, a novel neural network architecture featuring a unique building block known as the Blend module. This module incorporates binary and fixed-point convolutions in its main and skip paths, respectively. There is a judicious deployment of batch normalizations on both main and skip paths inside the Blend module and in between consecutive Blend modules. Additionally, we present a compiler and hardware architecture designed to map NeuroBlend models onto FPGA devices, aiming to minimize inference latency while maintaining high accuracy. Our NeuroBlend-20 (NeuroBlend-18) model, derived from ResNet-20 (ResNet-18) trained on CIFAR-10 (CIFAR-100), achieves 88.0% (73.73%) classification accuracy, outperforming state-of-the-art binary neural networks by 0.8% (1.33%), with an inference time of 0.38ms per image, 1.4x faster than previous FPGA implementation for BNNs. Similarly, our BlendMixer model for CIFAR-10 attains 90.6% accuracy(1.59% less than full precision MLPMixer), with a 3.5x reduction in model size compared to full precision MLPMixer. Furthermore, leveraging DSP blocks for 48-bit bitwise logic operations enables low-power FPGA implementation, yielding a 2.5x reduction in power consumption.