Invention Description Long-range image analysis presents a significant challenge in computer vision, primarily due to atmospheric turbulence. The spatiotemporal variation in the medium's refractive index causes light ray bending, resulting in image degradation, specifically blurring and geometric deformation. Traditional estimation methods for...

Invention Description Personalized human-sensing systems, especially in clinical and health applications, often struggle with limited user-specific data and significant variability between individuals. Differences in physiology, behavior, and environmental conditions can cause performance drops when models trained on general datasets are applied to...

Invention Description Collision-resilient quadrotors are designed to leverage impacts and perform agile maneuvers in cluttered environments; however, current models face a trade-off between two limited modes: Rigid protection and flexible adaptation. With rigid protection designs, there are safeguards that prevent damage, but they cannot deform to...

Invention Description Multimodal large language models (MLLMs) have shown strong potential in analyzing complex data types such as images, video, and audio, prompting growing interest in their use for medical applications. While several general-domain MLLMs have been adapted for healthcare tasks, including retinal imaging, their performance remains...

Invention Description Assessing honeybee worker populations is a critical index for monitoring colony health, productivity, and survivability in both agricultural and natural ecosystems. While essential for hive management, traditional population measurement techniques remain the industry standard despite being inherently labor-intensive and disruptive...

Invention Description Retrieval-Augmented Generative (RAG) models boost generative AI’s accuracy by connecting large language models (LLMs) with the most current, external, knowledge sources. RAG models are widely used in fact-checking, information retrieval, and AI-driven search engines. Despite their utility, adversarial threats can exploit...

Invention Description Conducting learning-based models on large-scale unstructured geometric data, particularly volumetric 3D meshes, remains a significant challenge. While previous methods have employed graph convolutional approaches, they suffer from high space complexity, limiting efficient mini-batch training, as well as fixed short-range feature...

Invention Description Heterogeneous composite materials, such as ceramic matrix composites (CMCs), are increasingly employed in high-temperature and extreme-environment applications due to their superior specific strength, thermal stability, and damage tolerance. The macroscopic response of these materials is governed by complex interactions among...

Invention Description Detecting bright point scatterers is important to quality assessments of sonar, radar and medical imaging systems, particularly as it pertains to resolution characterization. Prominent, or coherent, scatterers are typically detected using thresholding techniques in addition to statistical measures in the detection processing chain....

Invention Description Protein allostery is important in many biological processes and drug development. Understanding the mechanisms involved would be highly beneficial for therapeutic interventions. Existing techniques focus primarily on equilibrium dynamics and network analysis for allosteric interaction mapping. Unfortunately, these are limited...