Abstract: Light-emitting diode (LED) packages, and more particularly arrangements of multiple LED chips in LED packages are disclosed. Arrangements include different types, different dimensions, and/or different orientations of LED chips within LED packages and corresponding electrical connections. Further arrangements include individual cover structures having different dimensions for various LED chips to accommodate thickness variations of LED chips and/or thickness variations attributed to different elements of individual cover structures. Different cover structure elements may include lumiphoric materials, antireflective layers, filter layers, and polarization layers. By accounting for dimensional variations between LED chips and/or between cover structures within multiple-chip LED packages, aggregate light-emitting surfaces may be provided with improved emission uniformity.

Abstract: Solid-state lighting devices including light-emitting diodes (LEDs) and more particularly cover structure arrangements for packaged LED devices are disclosed. Cover structures include light-absorbing layers configured to absorb certain wavelengths of light while permitting other wavelengths to pass therethrough. Light-absorbing layers may include pigment materials of colors that absorb intended wavelengths of light. In certain aspects, an LED package may include an LED chip configured to emit light of a first peak wavelength and a cover structure that includes a light-absorbing layer with a pigment of a color that absorbs the first peak wavelength. Such an arrangement may be useful for embodiments that also include a lumiphoric material that converts a portion of the first peak wavelength to light of a second peak wavelength.

Abstract: A method for identifying compounds with threshold activity against a target macromolecule first generates multiple poses for each compound fragment in a plurality of compound fragments against an atomic model of the target macromolecule. This creates a collection of configurations, or a “pose set,” for the compound fragments. Each pose is associated with a subset of interaction features drawn from a broader set of such features. Each feature corresponds to a subregion of the target macromolecule's atomic model. Each pose is quantified by application to a physics model. This assigns a score to the interaction features associated with the poses. A binding hypothesis is formed for the macromolecule, using the collection of interaction features and their corresponding scores. From this hypothesis, derived compounds are identified. These derived compounds are tested for their activity against the macromolecule, leading to the identification of those that exhibit the desired threshold activity.

Abstract: The present disclosure relates to techniques for providing a liquid metal alloy in a light-emitting diode device that can both heal cracks formed in solder joints on the light-emitting diode (LED) device as well as improve thermal energy dissipation from the LED chips to improve the performance, reduce wear, and prolong the life of the LED chips. In an embodiment, a light-emitting diode device can include a liquid metal alloy containing gallium next to a solder joint, and when one or more cracks form, the liquid metal alloy can enter the cracks and solidify, healing the cracks. The liquid metal alloy can also be placed adjacent to, and in contact with the LED chip to transfer energy away from the LED chips.

Abstract: A method for identifying derived compounds exhibiting activity for a target macromolecule generates experiences. Each experience uses an initial compound in plurality of initial compounds to construct a derived compound through a hierarchical proximal policy. The policy has a parent molecular reaction model and a child reactant model that uses an environment of the target macromolecule. The parent model evaluates a plurality of molecular reactions. The child model evaluates a corresponding plurality of reactants for a selected molecular reaction. Using the plurality of experiences, the parameters of the parent model are updated in accordance with a first surrogate objective while the parameters of the child model are updated in accordance with a second surrogate objective. The generation of derived compounds and hierarchical proximal policy updating continues until convergence. Then, a subset of the derived compounds from the experiences is tested for activity against the target macromolecule.

Abstract: Light-emitting diode (LED) packages and more particularly LED packages with directional emission intensity and color uniformity are disclosed. LED packages include one or more LED chips on a submount with arrangements of light-altering materials and lumiphoric material layers that provide directional light emissions with improved color over angle uniformity. Light-altering materials are provided that cover sidewalls of LED chips while lumiphoric material layers cover LED chips and light-altering materials. Such LED packages may avoid the need to include encapsulation materials and/or lenses that would otherwise cover the lumiphoric material layers. As such, exterior light-exiting faces of LED packages are formed by surfaces of lumiphoric material layers.

Abstract: Light-emitting diode (LED) devices and more particularly lens structures in LED packages are disclosed. Lens structures include complex shapes for achieving various emission patterns in LED packages. Complex lens shapes include lens widths that are greater than corresponding widths of support elements, including lead frame structures or submount structures. Complex lens shapes further include inward depressions positioned relative to underlying LED chips for directing peak emission intensities off center relative to LED packages. Exemplary LED packages further include encapsulant layers positioned between lenses and underlying LED chips for providing one or more of improved surfaces for lens formation and improved adhesion.

Abstract: Systems and methods for determining pixel classification information using images depicting at least a portion of a whole slide image (WSI) of a stained tissue sample. A system can store a first image of the tissue sample at a first resolution, a second image of the tissue sample at a second resolution that is higher than the first resolution, and a third image of the tissue sample at a third resolution that is higher than the second resolution, the first, second, and third images depicting at least a portion of a same area of the tissue sample. The system can include be configured to generate first feature information based on the first image, generate second feature information based on the second image, and determine pixel classification information of at least a portion of the WSI based on the third image, the first feature information and second feature information.

Abstract: In various examples, three-dimensional (3D) object or feature detection and localization for autonomous and semi-autonomous systems and applications is described herein. Systems and methods are disclosed that use different types of sensors, such as an image sensor and a LIDAR sensor, to determine information associated with objects, such as traffic objects (e.g., traffic signs, traffic signals, traffic markings, etc.). To determine the information for an object, image data is processed to determine a bounding shape associated with the object. The bounding shape is then used to determine a 3D shape, such as a frustum, corresponding to the object. Additionally, points data generated using the LIDAR sensor, such as an occupancy map and/or a point cloud, is processed to identify a portion of the points associated with (e.g., located within) the 3D shape. This portion of the points may then be used to determine the information associated with the object.

Abstract: In various examples, three-dimensional (3D) object or feature detection and localization for autonomous and semi-autonomous systems and applications is described herein. Systems and methods are disclosed that use different types of sensors, such as an image sensor and a LIDAR sensor, to determine information associated with objects, such as traffic objects (e.g., traffic signs, traffic signals, traffic markings, etc.). To determine the information for an object, image data is processed to determine a bounding shape associated with the object. The bounding shape is then used to determine a 3D shape, such as a frustum, corresponding to the object. Additionally, points data generated using the LIDAR sensor, such as an occupancy map and/or a point cloud, is processed to identify a portion of the points associated with (e.g., located within) the 3D shape. This portion of the points may then be used to determine the information associated with the object.

Abstract: Solid-state lighting devices including light-emitting diodes (LEDs), and more particularly polarization structures for LED devices are disclosed. Polarization structures are disclosed that are integrated within light-emitting devices and are capable of receiving unpolarized light and providing polarized light that exits the light-emitting devices. Polarization structures may be formed on or in various surfaces within light-emitting devices, such as one or more surfaces of cover structures and/or LED chips. LED packages with multiple LED chips and multiple polarization structures are also disclosed. The LED chips may be arranged to be electrically activated and deactivated independently of one another such that corresponding LED packages are capable of electronically switching between different orientations of polarized and/or unpolarized light.

Abstract: Systems and methods for characterizing interactions between molecules and targets are provided. Candidate molecules are selected using first interaction scores for each molecule and a target. Molecular graphs of each molecule are inputted into a first and/or second model to retrieve a first plurality of on-target interaction features or a second plurality of off-target interaction features, respectively. Second interaction scores are obtained using the first and/or second plurality of features and evaluated to filter the plurality of candidate molecules. For each molecule, a third plurality of binding affinity interaction features and/or a fourth plurality of specificity interaction features are determined. The plurality of candidate molecules is filtered based at least on counts of features in the third and/or fourth plurality of features. Predictions of interaction between each molecule and the target are determined using at least the third and/or fourth plurality of features.

Abstract: Solid-state lighting devices including light-emitting diodes (LEDs), and more particularly integrated secondary optics into LED chip cover structures for improved optical emission of high intensity LEDs is disclosed. Optical elements are integrated as a secondary optic onto one or both surfaces of a chip cover structure, where the chip cover structure may be referred to as a primary optic. The integrated secondary optic may be formed directly on one or both surfaces of the chip cover structure. The integrated secondary optic is purposely built to be coupled with the light emission of the LED to emit a desired emission profile. In this regard, a final luminaire may be provided with increased efficiency either by improving the coupling of the LED into a conventional secondary optic or in some cases by removing the need for a conventional secondary optic all together.

Abstract: Solid-state lighting devices, and more particularly sidewall arrangements for light-emitting devices such as light-emitting diodes (LEDs) are disclosed. LED devices may include light-altering materials that are provided around peripheral sidewalls of LED chips without the need for a supporting submount or lead frame. The side layer around the peripheral sidewall of the LED chip can include an inner layer and an outer layer, each with different light altering properties. For example, the inner layer can be reflective so as to improve the light output and/or efficiency of the LED chip, while the outer layer can be absorptive so as to avoid interaction and/or crosstalk with neighboring LED chips. By having a reflective inner layer, and an absorptive outer layer, light output, sharpness, and contrast can be improved.

Abstract: Solid-state lighting devices including light-emitting diodes (LEDs) and, more particularly, reflectors for support structures in LED packages are disclosed. Support structures include arrangements of dielectric reflectors relative to LED chips and electrically conductive traces that are patterned on a submount. Dielectric reflectors include multiple dielectric layer structures that form a distributed Bragg reflector or, in some instances, an aperiodic Bragg reflector. Such dielectric reflectors may be arranged one or more of the electrically conductive traces and on portions of the submount uncovered by the electrically conducive traces to provide increased reflectivity across a variety of wavelengths provided by LED chips, including wavelengths in the ultraviolet spectrum.

Abstract: The present disclosure relates to techniques for providing a liquid metal alloy in a light-emitting diode device that can both heal cracks formed in solder joints on the light-emitting diode (LED) device as well as improve thermal energy dissipation from the LED chips to improve the performance, reduce wear, and prolong the life of the LED chips. In an embodiment, a light-emitting diode device can include a liquid metal alloy containing gallium next to a solder joint, and when one or more cracks form, the liquid metal alloy can enter the cracks and solidify, healing the cracks. The liquid metal alloy can also be placed adjacent to, and in contact with the LED chip to transfer energy away from the LED chips.

Abstract: Solid-state lighting devices including light-emitting diodes (LEDs) and lens arrangements for packaged LED devices are disclosed. An LED package may include one or more LED chips on a submount with a lens positioned on the submount to form a cavity. The one or more LED chips may reside in the cavity without direct encapsulation materials that would otherwise contact the one or more LED chips and any corresponding wirebonds. In this manner, the one or more LED chips may be driven with higher drive currents while reducing degradation and mechanical strain effects related to differences in coefficients of thermal expansion with typical encapsulant materials. LED packages may also be configured with one or more apertures that allow air flow between an interior volume of a cavity and an ambient environment outside the LED package to promote heat dissipation at higher drive currents.

Abstract: A light emitting device includes a LED having a light emitting first surface and a light emitting second surface that define a corner. A support layer is disposed to receive light emitted by the light emitting second surface and is disposed adjacent the corner. A luminophoric medium layer at least partially covers the light emitting first surface and the light emitting second surface where the luminophoric medium layer is at least partially supported by the support layer to prevent a narrowing of the luminophoric medium layer.

Abstract: Solid-state lighting devices including light-emitting diodes (LEDs), and more particularly support structures for LED packages are disclosed. Support structure arrangements are provided for LED packages with increased reflectivity. Support structures may include patterned electrically conductive materials that provide electrical connections and bonding surfaces for LED chips within the package, and bonding surfaces for cover structures in certain arrangements. Depending on the wavelengths of light emitted by the LED package, light reflectivity tradeoffs can exist for conductive materials that provide suitable electrical connections and bonding surfaces. Additional patterned layers with increased reflectivity may be provided on underlying patterned electrically conductive materials.