llm unlearning for cyber defense survey
a survey on methods, challenges, and emerging threats of making large language models forget sensitive or dangerous knowledge for cybersecurity.
aitag research
summaries filed under research
rl-guided nsga-ii with gray relational coefficients for portfolio optimization
a new algorithm combines reinforcement learning and gray relational analysis to improve multi-objective optimization for nasdaq portfolio selection.
aitighter tolerances catch more tensor kernel bugs
mining error distributions from cloud gpu runs yields per-operator tolerances that improve bug detection recall by 9.3 percentage points.
aiplanning-phase attacks on multi-agent llm systems
new research shows how injecting malicious prompts during the planning phase can corrupt entire multi-agent llm workflows.
aiisotonic conformal prediction
a new method for reliable uncertainty quantification that is computationally efficient and achieves self-calibration and prediction-conditional validity.
ailightweight 1d cnn classifies affective touch in soft companions
a compact 13.2k-parameter 1d cnn achieves high accuracy for recognizing emotional touch gestures on soft plush robots, using a new public dataset of 1326 sequences from 25 participants.
airater state bias in rlhf preference data
a new audit framework examines how rater stress and conditions can systematically shift preferences in reinforcement learning from human feedback, potentially biasing ai alignment.
aiquantum program generation must prioritize validity over scaling
a position paper argues that scaling language models for quantum circuit synthesis is misguided because valid circuits are exponentially rare, requiring verifier-centric architectures instead.
aireviewer precision does not guarantee critique uptake in math agents
a study on multi-agent math reasoning finds that higher reviewer precision does not lead to better answer correction, as critique often fails to change subsequent outputs.
aigraphdx: cost-aware multi-agent diagnosis framework
graphdx uses knowledge graphs and three agents to balance diagnostic accuracy and testing costs in sequential diagnosis.
aianovax runs a local voice assistant with typed agents and recovery
anovax is a desktop voice assistant that runs entirely on the user's computer, using an llm planner, typed executors, and adaptive recovery to control applications.
airetraining seeks stable signals
new research shows retraining converges to a fixed point when prediction targets have a small model-independent component, even under strong performativity.
aillms tested for technical market analysis
a study compares five large language models on tasks like candlestick recognition, trade signals, backtesting, and report comprehension.
aicorrecting noisy human labels in automated classifiers
a new method uses adjudicated cases to fix noisy human audit labels and debias analyses from automated classifiers.
aistochastic mgda gets faster with regularity-aware updates
new method improves convergence in multi-objective learning by using regularity conditions to make conflict-avoidant directions lipschitz continuous.
aiinterpretable medical classification with threshold-based naive bayes
a new framework uses chi-squared binarization and bernoulli naive bayes to create transparent, rule-based clinical classifiers with strong performance on benchmark medical datasets.
aicura 1t: a healthcare llm trained through self-evolution
a healthcare model trained via a human-gated self-evolution loop that improves through targeted data refinement rather than generic updates.
aihg-rag uses graph traversal for better structured knowledge retrieval
a new framework called hg-rag improves retrieval augmented generation by traversing hierarchical knowledge graphs instead of flat document stores, boosting accuracy on complex queries.
aiexplainable ai predicts clutter height for satellite ground station siting
a machine learning framework uses open geospatial data to predict representative clutter height, improving site selection for low earth orbit ground stations.
aiquantum u-net for wildfire detection from satellite images
researchers test a quantum-enhanced u-net on sentinel-2 imagery for wildfire segmentation, achieving modest results with variational circuits.
ai