Researchers investigate whether training policies to predict both actions and environmental changes using World Action Models improves robot manipulation learning from egocentric human videos.
AWS has launched the Claude apps gateway, a self-hosted control plane allowing organizations to manage access, costs, and policies for Claude Code and Claude Desktop.
A new generative framework utilizes large language models to model and predict consumer expectations regarding narrative story progression.
Researchers propose a new method for causal inference in whole-slide image classification to improve diagnostic accuracy in digital pathology.
The QDEvo framework integrates quality-diversity algorithms with large language models to prevent mode collapse in automated heuristic design.
This research proposes a method to improve the option-critic reinforcement learning framework by encouraging diversity in learned behaviors.
A new control framework integrates vision-based tracking and predictive modeling to improve autonomous target engagement for fixed-wing UAVs.
NVIDIA announced that its Nemotron 3 Ultra model achieved high accuracy and throughput on agent tasks when optimized with LangChain's Deep Agents harness.
A new federated reinforcement learning approach introduces constraint-aware aggregation to ensure safe operation in distributed energy microgrid systems.
Researchers developed a mathematical method to quantify the information an optimal policy holds about its environment to better understand internal world representations in AI.
A machine learning model was developed to estimate brain vascular age using cerebral blood flow velocity data from transcranial Doppler measurements.
Researchers propose a new method for topological navigation that utilizes pixel-level loops to improve mapping accuracy.
Researchers introduced a placebo-controlled evaluation methodology to more accurately measure the effectiveness of self-repair mechanisms in small code-generating language models.
The study evaluates the effectiveness of hierarchical planning in the LeWorldModel, finding that it does not consistently improve performance across all task horizons.
This paper introduces a methodological approach to measure how closely AI agents adhere to subjective expected utility maximization when making decisions under uncertainty.
This text provides a comprehensive overview of the mathematical principles underlying data science, covering topics from linear algebra to optimization.
A new neuro-symbolic method called Latent Grammar Flow enables the discovery of interpretable differential equations from data.
Researchers introduced SeqGPT, a transformer-based agent designed to solve complex combinatorial inverse problems in composite structure manufacturing.
The study proposes a metaphor-fluid design approach to allow voice user interfaces to dynamically adapt their conversational metaphors based on user context.
Researchers propose a distance-based method to quantify aleatoric and epistemic uncertainty within credal sets for machine learning classification tasks.
The Propheticus framework provides a machine learning approach to assist in the development and verification of reliable and secure software systems.
A new cascaded speech-LLM system is presented for the 2nd MLC-SLM challenge, combining diarization and recognition without requiring oracle labels.
A new framework for Genetic Network Programming aims to improve agentic AI by balancing exploration and exploitation within graph-based decision structures.
A weakly supervised pipeline has been developed to identify dairy farm locations using seasonal satellite imagery and existing map data.