ontology-amplified distillation for sovereign enterprise models
a study tests ontology-amplified distillation on a small language model for regulated finance, finding similar grounding to a frontier model but with limited statistical power.
aisummaries filed under research
a study tests ontology-amplified distillation on a small language model for regulated finance, finding similar grounding to a frontier model but with limited statistical power.
aia new method uses outlier events to falsify incorrect causal graphs, providing statistical tests with false positive control and power guarantees.
aia survey on in-context reinforcement learning methods that handle changing environments without test-time parameter updates.
aia new framework integrates expert constraints directly into scalable causal discovery algorithms, improving efficiency and accuracy.
aia python terminal game where sqlite handles movement, collision, enemies, combat, and pixel rendering using a recursive cte ray tracer.
aia two-stage method called unit uses deep representation learning to sharpen estimates of structural mediation parameters under a no essential heterogeneity assumption.
aia new model combines a cnn-lstm with a gaussian copula to jointly forecast multiple environmental variables while providing calibrated uncertainty estimates.
aicomputer scientist peter j. denning argues that ai cannot capture tacit human knowledge like common sense and culture, making true human-level intelligence impossible.
aia new benchmark metric reveals how small formatting changes in prompts can significantly alter model accuracy and parseability, challenging the reliability of current leaderboard rankings.
airesearchers use argumentation theory to break down retinal disease predictions into explainable parts, helping doctors trust ai decisions.
aistudy finds that structured message formats help or hurt llm agent relays depending on the model's capability tier, with strong models staying accurate and weak models degrading.
aia new method uses optimal transport coupling during flow matching training to align noise with molecular rewards, enabling controllable generation without extra models or gradients.
aia unified framework reveals that various knowledge distillation methods for large language models share a common mechanism: they force student models to use fewer interactions while zeroing out the rest.
aia new study finds decision-making activity in early sensory brain regions, challenging traditional models and offering insights for more efficient ai.
aia new benchmark evaluates ai agents on 46 long-horizon terminal tasks using dense intermediate rewards to measure progress, not just final outcomes.
aia new framework reduces adversarial robustness certification to a lattice traversal problem, enabling both sound and complete interval certifications for multilayer perceptrons.
aia mathematician directed an ai to formalize a mean-field derivation of the vlasov equation in lean 4, treating the process as a game with clear win conditions.
aia new framework extends deep gaussian processes to directed acyclic graphs, enabling better modeling of complex, partially observed processes with theoretical guarantees on information preservation.
aia new framework uses a generative ehr model as a patient digital twin to optimize sepsis treatment through model predictive control, adapting to changing goals without retraining.
aisigned symmetric quantization uses the extra negative value in signed integers to reduce clipping error without runtime overhead.
ai