graphdx: cost-aware multi-agent diagnosis framework
graphdx uses knowledge graphs and three agents to balance diagnostic accuracy and testing costs in sequential diagnosis.
aisummaries filed under research
graphdx uses knowledge graphs and three agents to balance diagnostic accuracy and testing costs in sequential diagnosis.
aianovax 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.
ainew research shows retraining converges to a fixed point when prediction targets have a small model-independent component, even under strong performativity.
aia study compares five large language models on tasks like candlestick recognition, trade signals, backtesting, and report comprehension.
aia new method uses adjudicated cases to fix noisy human audit labels and debias analyses from automated classifiers.
ainew method improves convergence in multi-objective learning by using regularity conditions to make conflict-avoidant directions lipschitz continuous.
aia new framework uses chi-squared binarization and bernoulli naive bayes to create transparent, rule-based clinical classifiers with strong performance on benchmark medical datasets.
aia healthcare model trained via a human-gated self-evolution loop that improves through targeted data refinement rather than generic updates.
aia new framework called hg-rag improves retrieval augmented generation by traversing hierarchical knowledge graphs instead of flat document stores, boosting accuracy on complex queries.
aia machine learning framework uses open geospatial data to predict representative clutter height, improving site selection for low earth orbit ground stations.
airesearchers test a quantum-enhanced u-net on sentinel-2 imagery for wildfire segmentation, achieving modest results with variational circuits.
aia new framework called cgap uses homogeneity analysis to create color-coded heatmaps for exploring complex categorical datasets.
aia new method adjusts prompt weights per class to improve zero-shot image classification with vision-language models.
ainew analysis tightens spectral norm estimates for random geometric graphs, improving guarantees for synchronization and latent geometry recovery.
aia study finds the best way to mix real and teacher-generated data for training rectified flow models, with a simple rule to improve performance.
aia new control layer certifies per-domain contamination budgets in retrieval systems without query-time labels, ensuring worst-domain guarantees.
airegnetagents uses ai agents to identify regulatory drivers in cancer by comparing bulk tumor and single-cell gene networks.
aia hierarchical architecture combines hebbian learning, multi-agent reinforcement learning, and meta-learning to control drone swarms in rescue missions.
aimoonshot ai's kimi k3 is a 2.8 trillion parameter model that tops some benchmarks but costs more than previous chinese releases.
aimira murati's thinking machines lab released inkling, a 975b parameter mixture-of-experts multimodal model under apache 2.0 license, aimed at fine-tuning rather than frontier performance.
ai