AINeutralarXiv – CS AI · Mar 57/10
🧠Researchers developed a new method to detect reward-hacking behavior in fine-tuned large language models by monitoring internal activations during text generation, rather than only evaluating final outputs. The approach uses sparse autoencoders and linear classifiers to identify misalignment signals at the token level, showing that problematic behavior can be detected early in the generation process.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce XAInomaly, an explainable AI framework using a Semi-supervised Deep Contractive Autoencoder for detecting anomalies in Open RAN (O-RAN) networks. The system addresses the critical need for interpretable machine learning in complex wireless infrastructure by combining generative modeling with explainability techniques to identify network traffic deviations while maintaining transparency in decision-making.
AINeutralarXiv – CS AI · Jun 85/10
🧠Researchers propose STDAE, a spatio-temporal deep learning framework that reconstructs missing ramp flow data at highway interchanges using mainline traffic information. The model matches the performance of systems with actual ramp data, addressing a critical infrastructure gap where real-time ramp detectors are unavailable.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers propose Product-Aware Deep Autoencoders to improve anomaly detection in multi-product manufacturing environments, addressing a critical vulnerability where traditional global models fail to detect cyber-physical attacks. Testing on the Tennessee Eastman Process benchmark demonstrates the approach achieves 100% detection accuracy versus 22.2% for conventional models under attack scenarios.
AINeutralarXiv – CS AI · Jun 25/10
🧠Researchers propose a hybrid machine learning framework combining data-level and algorithm-level balancing techniques to address imbalanced regression problems, where underrepresented target values typically degrade model performance. The framework integrates adaptive partitioning, conditional variational autoencoders, strategic oversampling, and a novel weighted loss function to improve predictions on rare but important cases.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers present a Transformer Autoencoder framework with local attention mechanisms designed to detect non-technical losses (electricity theft) in power grids using sparse, irregular time series data. The model demonstrates superior performance in risk estimation for Greek electrical systems compared to existing methods, achieving high recall and precision while effectively handling data collection irregularities.
AIBullisharXiv – CS AI · Mar 55/10
🧠Researchers developed Cryo-SWAN, a new AI autoencoder network that uses wavelet decomposition to better represent 3D molecular structures from cryo-electron microscopy data. The model outperforms existing 3D autoencoders on multiple datasets and can integrate with diffusion models for molecular shape generation and denoising.
AINeutralarXiv – CS AI · Mar 125/10
🧠Researchers developed a multi-layer ensemble defense system to protect AI-powered Network Intrusion Detection Systems (NIDS) from adversarial attacks. The solution combines stacking classifiers with autoencoder validation and adversarial training, demonstrating improved resilience against GAN and FGSM-generated attacks on security datasets.
AIBullisharXiv – CS AI · Mar 95/10
🧠Researchers introduce CLAIRE, a deep learning framework that combines unsupervised autoencoders with supervised classification for fault detection in industrial manufacturing. The system transforms high-dimensional sensor data into compact representations and uses explainable AI techniques to identify key features contributing to fault predictions.
AINeutralarXiv – CS AI · Feb 274/106
🧠Researchers introduce a theoretical framework connecting multi-chart autoencoders in manifold learning with classical vector bundle theory and characteristic classes. The approach treats collections of locally trained encoder-decoder pairs as learned atlases on manifolds, enabling computation of differential-topological invariants and providing algorithmic criteria for detecting orientability.
