In various examples, a timeline of text prompt(s) specifying any number of (e.g., sequential and/or simultaneous) actions may be specified or generated, and the timeline may be used to drive a diffusion model to generate compositional human motion that implements the arrangement of action(s) specified by the timeline. For example, at each denoising step, a pre-trained motion diffusion model may be used to denoise a motion segment corresponding to each text prompt independently of the others, and the resulting denoised motion segments may be temporally stitched, and/or spatially stitched based on body part labels associated with each text prompt. As such, the techniques described herein may be used to synthesize realistic motion that accurately reflects the semantics and timing of the text prompt(s) specified in the timeline.
In various examples, motifs, watermarks, and/or signature inputs are applied to a deep neural network (DNN) to detect faults in underlying hardware and/or software executing the DNN. Information corresponding to the motifs, watermarks, and/or signatures may be compared to the outputs of the DNN generated using the motifs, watermarks and/or signatures. When a the accuracy of the predictions are below a threshold, or do not correspond to the expected predictions of the DNN, the hardware and/or software may be determined to have a fault-such as a transient, an intermittent, or a permanent fault. Where a fault is determined, portions of the system that rely on the computations of the DNN may be shut down, or redundant systems may be used in place of the primary system. Where no fault is determined, the computations of the DNN may be relied upon by the system.
G05D 1/00 - Commande de la position, du cap, de l'altitude ou de l'attitude des véhicules terrestres, aquatiques, aériens ou spatiaux, p. ex. utilisant des pilotes automatiques
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
G06V 10/764 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant la classification, p. ex. des objets vidéo
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 10/98 - Détection ou correction d’erreurs, p. ex. en effectuant une deuxième exploration du motif ou par intervention humaineÉvaluation de la qualité des motifs acquis
G06V 20/56 - Contexte ou environnement de l’image à l’extérieur d’un véhicule à partir de capteurs embarqués
3.
PERSONALIZING INTERACTIVE AGENTS FOR CONVERSATIONAL AI SYSTEMS AND APPLICATIONS
In various examples, systems and methods are disclosed relating to engaging users through a personalized interface. One system includes at least one processor configured to determine first conversation history with a user. The at least one processor further configured to determine a response by applying the first conversation history with the user to a machine learning model, wherein the machine learning model is updated using user input indicative of an interest level of the user for each of a plurality of candidate responses to a question, a content of the question is determined by the at least one processor, and the plurality of candidate responses are determined using the machine learning model, and the machine learning model is updated using the user input as a reward signal.
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
G06F 40/40 - Traitement ou traduction du langage naturel
H04L 51/216 - Gestion de l'historique des conversations, p. ex. regroupement de messages dans des sessions ou des fils de conversation
Apparatuses, systems, and techniques to generate one or more second masks to modify a second portion of a neural network based, at least in part, on one or more first masks of a first portion of the neural network from which the second portion of the neural network depends. In at least one embodiment, modifications one portion of a neural network are propagated to other portions of the neural network based on dependencies between these portions and one or more tensor masks.
A system and method for an on-demand shuttle, bus, or taxi service able to operate on private and public roads provides situational awareness and confidence displays. The shuttle may include ISO 26262 Level 4 or Level 5 functionality and can vary the route dynamically on-demand, and/or follow a predefined route or virtual rail. The shuttle is able to stop at any predetermined station along the route. The system allows passengers to request rides and interact with the system via a variety of interfaces, including without limitation a mobile device, desktop computer, or kiosks. Each shuttle preferably includes an in-vehicle controller, which preferably is an AI Supercomputer designed and optimized for autonomous vehicle functionality, with computer vision, deep learning, and real time ray tracing accelerators. An AI Dispatcher performs AI simulations to optimize system performance according to operator-specified system parameters.
User reaction data is received from one or more user devices of a user. The user reaction data indicates a reaction of the user to a simulation provided via at least one of the user devices. The user reaction data is provided as input to an artificial intelligence (AI) model. Simulation update data is determined based on output(s) of the AI model, the simulation update data indicating one or more updates to the simulation based on an experience of the user in view of the provided user reaction data. A model file associated with the simulation is updated to reflect the one or more updates indicated by the simulation data. The updated model file, when executed, creates a rendering of the updated simulation. The updated simulation is provided to the user via the at least one of the user devices based on an execution of the updated model file.
Alias-free diffusion neural network models configured to convert input Gaussian noise and additional conditioning signals to images or video utilizing translation equivariant layers and noise signals generated by continuous Gaussian processes. The models may comprise a U-net encoder/decoder structure with noise samples derived from a Gaussian process using techniques such as Random Fourier Features approximation.
Apparatuses, systems, and techniques to perform a neural network to select a dataset. In at least one embodiment, for example, a neural network calculates an expected relevance of data of a dataset subset, where said subset is portioned based, at least in part, on an amount of available storage. In at least one embodiment, as another example, a processor is to cause one or more neural networks to identify one or more first portions of first information to be used by one or more neural networks to generate second information, wherein one or more neural networks are to identify one or more first portions based, at least in part, on an amount of available storage.
Apparatuses, systems, and techniques are to modify a precision and/or sparsity of one or more neural network layers. In at least one embodiment, a precision and/or sparsity of one or more neural network layers are based, at least in part on, a comparison of activations of a sparse version and a dense version of a neural network.
Readout logic for bit-storing cells of a machine memory wherein the bit-storing cells comprise first read/write voltage domain crossings includes a read latch coupled to the bit-storing cell via a read bitline and the read latches include second read/write voltage domain crossings configured in pull-down networks of the read latches.
Systems and methods are disclosed that relate to testing processing elements of an integrated processing system. A first system test may be performed on a first processing element of an integrated processing system. The first system test may be based at least on accessing a test node associated with the first processing element. The first system test may be accessed using a first local test controller. A second system test may be performed on a second processing element of the integrated processing system. The second system test may be based at least on accessing a second test node associated with the second processing element. The second system test may be accessed using a second local test controller.
B60W 50/02 - Détails des systèmes d'aide à la conduite des véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier pour préserver la sécurité en cas de défaillance du système d'aide à la conduite, p. ex. en diagnostiquant ou en palliant à un dysfonctionnement
B60W 50/00 - Détails des systèmes d'aide à la conduite des véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier
12.
CIRCADIAN RHYTHM-BASED DATA AUGMENTATION FOR OCCUPANT STATE ANALYSIS
In various examples, circadian rhythm-based data augmentation for drowsiness detection systems and applications are provided. Embodiments described herein may produce an estimated circadian rhythm for a test subject and/or vehicle driver or other machine operator or occupant, and use the pattern of that circadian rhythm to correct, confirm, calibrate, or otherwise augment drowsiness assessments derived from video image data. The position of a person in the context of their process C circadian cycle may be used as indication of their level of drowsiness. An estimated process C circadian cycle may be used to generate more accurate ground truth training data for training machine learning models, and may be used by real-time, in-vehicle drowsiness detection systems that infer driver drowsiness levels based on captured images. In various embodiments, a circadian rhythm drowsiness estimate may be used to correct, calibrate, augment, and/or replace a drowsiness score predicted by a machine learning model.
B60W 40/08 - Calcul ou estimation des paramètres de fonctionnement pour les systèmes d'aide à la conduite de véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier liés aux conducteurs ou aux passagers
B60W 50/00 - Détails des systèmes d'aide à la conduite des véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier
G06V 10/34 - Lissage ou élagage de la formeOpérations morphologiquesSquelettisation
G06V 20/59 - Contexte ou environnement de l’image à l’intérieur d’un véhicule, p. ex. concernant l’occupation des sièges, l’état du conducteur ou les conditions de l’éclairage intérieur
G06V 40/10 - Corps d’êtres humains ou d’animaux, p. ex. occupants de véhicules automobiles ou piétonsParties du corps, p. ex. mains
13.
RECOMMENDATION SYSTEM USING RETRIEVAL-AUGMENTED GENERATION
In various examples, a technique for recommending items is disclosed that includes receiving a request to recommend an item. The technique further includes generating, based on the request, one or more query tags, the one or more query tags including one or more preferred tags, at least one of the preferred tags specifying an item of interest. The technique also includes generating one or more subqueries based on the one or more query tags. The technique still further includes generating, based on the one or more subqueries, a query vector in an embedding space of the vector database. The technique further includes identifying, in the vector database and using the query vector, a plurality of candidate items. The technique still further includes selecting a recommended item from the plurality of candidate items based on the request.
In various examples, circadian rhythm-based data augmentation for drowsiness detection systems and applications are provided. Embodiments described herein may produce an estimated circadian rhythm for a test subject and/or vehicle driver or other machine operator or occupant, and use the pattern of that circadian rhythm to correct, confirm, calibrate, or otherwise augment drowsiness assessments derived from video image data. The position of a person in the context of their process C circadian cycle may be used as indication of their level of drowsiness. An estimated process C circadian cycle may be used to generate more accurate ground truth training data for training machine learning models, and may be used by real-time, in-vehicle drowsiness detection systems that infer driver drowsiness levels based on captured images. In various embodiments, a circadian rhythm drowsiness estimate may be used to correct, calibrate, augment, and/or replace a drowsiness score predicted by a machine learning model.
B60W 60/00 - Systèmes d’aide à la conduite spécialement adaptés aux véhicules routiers autonomes
G06V 10/774 - Génération d'ensembles de motifs de formationTraitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source méthodes de Bootstrap, p. ex. "bagging” ou “boosting”
G06V 20/59 - Contexte ou environnement de l’image à l’intérieur d’un véhicule, p. ex. concernant l’occupation des sièges, l’état du conducteur ou les conditions de l’éclairage intérieur
Apparatuses, systems, and techniques are to modify a precision and/or sparsity of one or more neural network layers. A precision and/or sparsity of one or more neural network layers are based, at least in part on, a comparison of activations of a sparse version and a dense version of a neural network.
In various examples, a media stream may be received by a re-encode system that may leverage a recode engine to convert (e.g., at an interval, based on a request, etc.) an inter-frame associated with the media stream to an intra-frame. The intra-frame may be converted from the inter-frame using parameters or other information associated with and received with the media stream. The converted intra-frame may be merged into an updated segment of the media stream in place of the original inter-frame to enable storage of the updated segment—or a portion thereof—for later use.
H04N 21/4402 - Traitement de flux élémentaires vidéo, p. ex. raccordement d'un clip vidéo récupéré d'un stockage local avec un flux vidéo en entrée ou rendu de scènes selon des graphes de scène du flux vidéo codé impliquant des opérations de reformatage de signaux vidéo pour la redistribution domestique, le stockage ou l'affichage en temps réel
A63F 13/86 - Regarder des jeux joués par d’autres joueurs
H04N 19/184 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c.-à-d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant des bits, p. ex. de flux vidéo compressé
H04N 19/50 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage prédictif
H04N 21/433 - Opération de stockage de contenu, p. ex. opération de stockage en réponse à une requête de pause ou opérations de cache
H04N 21/434 - Désassemblage d'un flux multiplexé, p. ex. démultiplexage de flux audio et vidéo, extraction de données additionnelles d'un flux vidéoRemultiplexage de flux multiplexésExtraction ou traitement de SIDésassemblage d'un flux élémentaire mis en paquets
H04N 21/478 - Services additionnels, p. ex. affichage de l'identification d'un appelant téléphonique ou application d'achat
Apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to detect objects from a plurality of image frames. In at least one embodiment, a plurality of image frames are fused into a feature map using one or more neural networks. In at least one embodiment, a plurality of image frames are processed using one or more neural networks to detect objects in a 3D space.
G06V 10/77 - Traitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source
G06V 10/74 - Appariement de motifs d’image ou de vidéoMesures de proximité dans les espaces de caractéristiques
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
18.
LANGUAGE MODEL-ASSISTED SYSTEM INSTALLATION, DIAGNOSTICS, AND DEBUGGING
Disclosed are apparatuses, systems, and techniques that train and use trained language models to assist users with complex systems installation, troubleshooting, and/or maintenance. The techniques include receiving, via a user interface (UI), a natural language (NL) query associated with one or more malfunction indicators indicative of a malfunction state of a system, providing, to a language model (LM) trained using a documentation associated with the system, an input having a prompt that is based at least on the NL query. The techniques further include receiving, from the LM, a response to the NL query, the response having one or more instructions associated with resolution of the malfunction state of the system and causing the UI to display the response.
In various examples, properties may be determined for image regions, where the image regions are indicated by output data generated using MLMs. An encoder may use the properties to generate encoded images using encoding quality settings for the image regions. When an encoded image is decoded and applied to the MLMs, corresponding output data may indicate an image region which is likely to correspond to an encoded image region of the encoded image, and which may be applied to at least one MLM. Thus, the properties for encoding an image region to an encoded image can be adapted to control the visual quality of an image region determined from a decoded version of the encoded image. The properties may be determined based at least on performance metric values for the MLMs or based at least on a ranking of the image regions.
H04N 19/42 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques caractérisés par les détails de mise en œuvre ou le matériel spécialement adapté à la compression ou à la décompression vidéo, p. ex. la mise en œuvre de logiciels spécialisés
H04N 19/154 - Qualité visuelle après décodage mesurée ou estimée de façon subjective, p. ex. mesure de la distorsion
H04N 19/167 - Position dans une image vidéo, p. ex. région d'intérêt [ROI]
H04N 19/176 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c.-à-d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p. ex. un objet la zone étant un bloc, p. ex. un macrobloc
20.
MAP DOWNLOAD AND STORAGE MANAGEMENT FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
The present disclosure relates to intelligent download and management of map data. For example, a machine may use map data stored thereon to perform operations. The map data may be organized according to multiple data layers based at least on different types of map data used by multiple different processes of a processing system of a machine. The different processes may be configured to perform one or more operations associated with a navigation system. A computing system may be configured to cause communication of one or more individual data layers to the processing system based at least on one or more individual prioritizations associated with the one or more individual data layers. The individual prioritizations may be based at least on a timing of processing of the individual data layers by one or more processes that are respectively associated with the individual data layers.
B60W 50/06 - Détails des systèmes d'aide à la conduite des véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier pour améliorer la réponse dynamique du système d'aide à la conduite, p. ex. pour améliorer la vitesse de régulation, ou éviter le dépassement de la consigne ou l'instabilité
B60W 60/00 - Systèmes d’aide à la conduite spécialement adaptés aux véhicules routiers autonomes
G06F 9/48 - Lancement de programmes Commutation de programmes, p. ex. par interruption
G06F 16/29 - Bases de données d’informations géographiques
21.
GAZE DETERMINATION USING ONE OR MORE NEURAL NETWORKS
Apparatuses, systems, and techniques are presented to predict gaze of an observer. In at least one embodiment, a network is trained to predict a gaze of one or more users based, at least in part, on one or more gazes corresponding to objects not always visible to the one or more users.
G06F 3/01 - Dispositions d'entrée ou dispositions d'entrée et de sortie combinées pour l'interaction entre l'utilisateur et le calculateur
G06F 18/21 - Conception ou mise en place de systèmes ou de techniquesExtraction de caractéristiques dans l'espace des caractéristiquesSéparation aveugle de sources
G06N 3/04 - Architecture, p. ex. topologie d'interconnexion
The present invention facilitates efficient and effective utilization of unified virtual addresses across multiple components. In one exemplary implementation, an address allocation process comprises: establishing space for managed pointers across a plurality of memories, including allocating one of the managed pointers with a first portion of memory associated with a first one of a plurality of processors; and performing a process of automatically managing accesses to the managed pointers across the plurality of processors and corresponding memories. The automated management can include ensuring consistent information associated with the managed pointers is copied from the first portion of memory to a second portion of memory associated with a second one of the plurality of processors based upon initiation of an accesses to the managed pointers from the second one of the plurality of processors.
In various examples, live perception from sensors of a vehicle may be leveraged to generate object tracking paths for the vehicle to facilitate navigational controls in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs-such as feature descriptor maps including feature descriptor vectors corresponding to objects included in a sensor(s) field of view. The outputs may be decoded and/or otherwise post-processed to reconstruct object tracking and to determine proposed or potential paths for navigating the vehicle.
G06V 20/58 - Reconnaissance d’objets en mouvement ou d’obstacles, p. ex. véhicules ou piétonsReconnaissance des objets de la circulation, p. ex. signalisation routière, feux de signalisation ou routes
B60W 60/00 - Systèmes d’aide à la conduite spécialement adaptés aux véhicules routiers autonomes
G06F 18/213 - Extraction de caractéristiques, p. ex. en transformant l'espace des caractéristiquesSynthétisationsMappages, p. ex. procédés de sous-espace
G06T 7/246 - Analyse du mouvement utilisant des procédés basés sur les caractéristiques, p. ex. le suivi des coins ou des segments
G06V 10/22 - Prétraitement de l’image par la sélection d’une région spécifique contenant ou référençant une formeLocalisation ou traitement de régions spécifiques visant à guider la détection ou la reconnaissance
G06V 10/46 - Descripteurs pour la forme, descripteurs liés au contour ou aux points, p. ex. transformation de caractéristiques visuelles invariante à l’échelle [SIFT] ou sacs de mots [BoW]Caractéristiques régionales saillantes
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
24.
NEURAL NETWORKS TO IDENTIFY OBJECTS IN MODIFIED IMAGES
Apparatuses, systems, and techniques to identify objects within one or more images. In at least one embodiment, objects are identified in an image using one or more neural networks based, at least in part, on one or more features of the one or more images and one or more features of one or more modified versions of the one or more images.
Apparatuses, systems, and techniques estimate parameters to train one or more neural networks based on uniqueuss of training data. In at least one embodiment, a subset of training data is selected and used to estimate parameters to train one or more neural networks, based on, for example, uniqueness of training data.
G06V 10/75 - Organisation de procédés de l’appariement, p. ex. comparaisons simultanées ou séquentielles des caractéristiques d’images ou de vidéosApproches-approximative-fine, p. ex. approches multi-échellesAppariement de motifs d’image ou de vidéoMesures de proximité dans les espaces de caractéristiques utilisant l’analyse de contexteSélection des dictionnaires
G16H 30/20 - TIC spécialement adaptées au maniement ou au traitement d’images médicales pour le maniement d’images médicales, p. ex. DICOM, HL7 ou PACS
26.
AUTOMATIC SPEECH RECOGNITION WITH TARGET WORD SPOTTING
Disclosed are apparatuses, systems, and techniques that may use machine learning for implementing automatic speech recognition (ASR) facilitated with a search for target words. The techniques include applying an ASR model to audio data to generate an ASR output representative of a likelihood that the audio data comprises one or more spoken speech units (SUs), generating, using the ASR output, a first score characterizing a likelihood that the audio data comprises a first word, wherein the first word comprises a dictionary word, generating, using the ASR output, a second score characterizing a likelihood that the audio data comprises a second word, wherein the second word comprises a word of a plurality of target words, wherein the plurality of target words is identified based at least on a context of the audio data, and predicting, using the first score and the second score, a spoken word associated with the audio data.
A system can include a memory and a processing device, operatively coupled to the memory, to perform operations including receiving, from a storage device, a data block of a blockchain, wherein the data block includes a data block payload comprising test data of an in-system test to be performed on a target device, which is external with respect to the storage device, determining whether the data block is valid by authenticating the data block, and in response to determining that the data block is valid, performing the in-system test on the target device by processing at least a portion of the test data extracted from the data block payload.
In various embodiments, an inductor package comprising an inductor that produces a first magnetic flux, and a conductive material disposed on the inductor that provides a reflective magnetic flux that at least partially cancels the first magnetic flux. Other embodiments include a circuit board comprising a printed circuit board (PCB); and at least one inductor package fixed to the PCB, the inductor package including an inductor that produces a first magnetic flux, and a conductive material shielding disposed over at least a portion of a surface of the inductor that provides a reflective magnetic flux that at least partially cancels the first magnetic flux.
Systems and methods to implement a technique for determining an environment importance sampling function. An environment map may be provided where lighting information about the environment is known, but where certain pixels within a scene associated with the environment map are shaded. From these shaded pixels, rays may be drawn in random directions to determine whether the rays are occluded or can interact with the environment map, which provides an indication of a source of lighting that can be used for light transport simulations. A mask may be generated based on these occlusions and used to update the environment importance sampling function.
Apparatuses, systems, and techniques to help identify one or more directions to transmit a first fifth generation new radio (“5G NR”) signal. In at least one embodiment, said one or more identified directions to be used to transmit a first 5G NR signal is based, at least in part, on channel state information of one or more second 5G NR signals.
H04B 7/06 - Systèmes de diversitéSystèmes à plusieurs antennes, c.-à-d. émission ou réception utilisant plusieurs antennes utilisant plusieurs antennes indépendantes espacées à la station d'émission
A device includes a printed circuit board (PCB) including a signal trace electrically coupled to a signal via. The device further includes a slot ground configured to reduce signal interference with respect to the signal via. The slot ground includes a slot formed in the PCB at least partially surrounding the signal via. The slot ground further includes metal plating on a wall of the slot. The metal plating is electrically coupled to a ground plane of the PCB. The slot ground further includes resin at least partially filling the slot.
In various examples, an encrypted file such as one representing an encrypted game build may be distributed with an encrypted content-encryption key that was used to encrypt the file and/or an identifier associated with a key-encryption key that was used to encrypt the content-encryption key. An authorized recipient may extract the encrypted content-encryption key and the identifier from the encrypted file, use the identifier to retrieve a corresponding key-encryption key, use the key-encryption key to decrypt the encrypted content-encryption key, and use the decrypted content-encryption key to decrypt the file. Taking an encrypted game build for cloud gaming as an example, a cloud gaming platform may decrypt, attach, and mount the build (e.g., as a block device or other virtual data disk) using the decrypted content-encryption key. Accordingly, the game build may be installed and executed without the need to distribute the game build to the end user.
A dense wave division multiplex (DWDM) receiver includes receiver lanes each configured to detect signals encoded in a different electromagnetic frequency band. The DWDM receiver applies a clock signal received on a variable one of the receiver lanes to lock a frequency of an injection locked oscillator (ILO) of a clock distribution network, and receiver lanes that are configured to receive data signals generate resonance on the clock distribution network. The resonant signal from the clock distribution network is applied to sample the received data signals.
Apparatuses, systems, and techniques to adjust one or more signal-to-noise ratios. In at least one embodiment, a processor includes one or more circuits to cause one or more signal-to-noise ratios to be adjusted by a variable amount based, at least in part, on a number of indications received by the processor indicating whether a signal was interpreted successfully.
Apparatuses, systems, and techniques to perform neural networks. In at least one embodiment, one or more neural networks are used to identify one or more video encoding artifacts based, at least in part, on a plurality of different video encoding settings.
Apparatuses, systems, and techniques are to modify a neural network according to hardware type. In at least one embodiment, one or more masks are used with a neural network to be deployed on a specific GPU hardware platform.
G06N 3/063 - Réalisation physique, c.-à-d. mise en œuvre matérielle de réseaux neuronaux, de neurones ou de parties de neurone utilisant des moyens électroniques
In various examples, a file such as one representing a game build may be encrypted using a (e.g., randomly generated) content-encryption key, and the content-encryption key may be encrypted using a key-encryption key. The encrypted content-encryption key may be included in the encrypted file (e.g., as metadata), and an identifier associated with the key-encryption key may be included in the encrypted file (e.g., as part of an entropy tag appended to the filename). As such, the encrypted file may be securely distributed (e.g., via a content distribution network). Taking an encrypted game build for cloud gaming as an example, a game developer may encrypt a game build (e.g., as an encrypted disk) and distribute the encrypted build through an interface such as a developer portal of a cloud gaming platform, which may distribute the encrypted build to various data centers and/or geographic zones of the cloud gaming platform.
Embodiments of the present disclosure may include a method and system for performing one or more operations based on a visibility confidence model. In some embodiments, the method may include generating a visibility confidence model which may indicate a level of confidence in sensor data that may correspond to individual sub-sections of an aggregate field of view. In some embodiments, the levels of confidence may be determined based on one or more errors associated with an individual sensor, one or more gross-level degradations, one or more fine-level degradations, or one or more occlusions being present in the sensor data. In some embodiments, the method may additionally include performing one or more operations based on the visibility confidence model or the level of confidence corresponding to individual sub-areas of the aggregate field of view.
B60W 60/00 - Systèmes d’aide à la conduite spécialement adaptés aux véhicules routiers autonomes
B60W 50/02 - Détails des systèmes d'aide à la conduite des véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier pour préserver la sécurité en cas de défaillance du système d'aide à la conduite, p. ex. en diagnostiquant ou en palliant à un dysfonctionnement
39.
GENERATING DIALOGUE FLOWS FROM UNLABELED CONVERSATION DATA USING LANGUAGE MODELS
In various examples, a technique for generating dialogue flows includes inputting a plurality of conversations into a machine learning model. The technique also includes generating, based at least on the machine learning model processing the plurality of conversations, a plurality of annotations comprising a plurality of constrained semantic representations for respective messages of sequences of messages included in the plurality of conversations. The technique further includes generating one or more dialogue flows from the plurality of constrained semantic representations and causing a conversational output to be generated based on the one or more dialogue flows.
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
G06F 16/901 - IndexationStructures de données à cet effetStructures de stockage
G06F 40/35 - Représentation du discours ou du dialogue
Apparatuses, systems, and techniques are to modify a neural network according to hardware type. In at least one embodiment, one or more masks are used with a neural network to be deployed on a specific GPU hardware platform.
Apparatuses, systems, and techniques to perform neural networks. In at least one embodiment, one or more neural networks are used to identify one or more video encoding artifacts based, at least in part, on a plurality of different video encoding settings.
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/40 - ScènesÉléments spécifiques à la scène dans le contenu vidéo
H04N 19/154 - Qualité visuelle après décodage mesurée ou estimée de façon subjective, p. ex. mesure de la distorsion
H04N 19/172 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par l’unité de codage, c.-à-d. la partie structurelle ou sémantique du signal vidéo étant l’objet ou le sujet du codage adaptatif l’unité étant une zone de l'image, p. ex. un objet la zone étant une image, une trame ou un champ
H04N 19/196 - Procédés ou dispositions pour le codage, le décodage, la compression ou la décompression de signaux vidéo numériques utilisant le codage adaptatif caractérisés par le procédé d’adaptation, l’outil d’adaptation ou le type d’adaptation utilisés pour le codage adaptatif étant spécialement adaptés au calcul de paramètres de codage, p. ex. en faisant la moyenne de paramètres de codage calculés antérieurement
42.
NEURAL NETWORKS TO IDENTIFY OBJECTS IN MODIFIED IMAGES
Apparatuses, systems, and techniques to identify objects within one or more images. In at least one embodiment, objects are identified in an image using one or more neural networks based, at least in part, on one or more features of the one or more images and one or more features of one or more modified versions of the one or more images.
G06V 10/44 - Extraction de caractéristiques locales par analyse des parties du motif, p. ex. par détection d’arêtes, de contours, de boucles, d’angles, de barres ou d’intersectionsAnalyse de connectivité, p. ex. de composantes connectées
G06V 10/56 - Extraction de caractéristiques d’images ou de vidéos relative à la couleur
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
43.
LOW MOTION BLUR DISPLAYS WITH VARIABLE REFRESH RATES
Disclosed are systems and techniques for low motion blue displays with variable refresh rates. The techniques include generating a predicted frame duration for a first frame, determining an actual frame duration for the first frame, and causing the first frame to be displayed by operating a backlight of a display in a first mode. Operating the backlight of the display in the first mode includes pulsing the backlight of the display for the first frame at a first time for a fraction of the predicted frame duration and pulsing the backlight of the display for the first frame at a second time based on a difference between the predicted frame duration and the actual frame duration.
G09G 3/34 - Dispositions ou circuits de commande présentant un intérêt uniquement pour l'affichage utilisant des moyens de visualisation autres que les tubes à rayons cathodiques pour la présentation d'un ensemble de plusieurs caractères, p. ex. d'une page, en composant l'ensemble par combinaison d'éléments individuels disposés en matrice en commandant la lumière provenant d'une source indépendante
According to various embodiments, a processing subsystem includes: a processor mounted on a first printed circuit board that is oriented parallel to a first plane; a heat sink thermally coupled to the processor; a second printed circuit board that is communicatively coupled to the first printed circuit board and oriented parallel to a second plane, wherein the second plane is not parallel with the first plane; and at least one cooling fan that is positioned to direct a cooling fluid through the heat sink in a direction parallel to the first plane.
Disclosed are systems and techniques for low motion blue displays with variable refresh rates. The techniques include generating a predicted frame duration for a first frame, determining an actual frame duration for the first frame, and causing the first frame to be displayed by operating a backlight of a display in a first mode. Operating the backlight of the display in the first mode includes pulsing the backlight of the display for the first frame at a first time for a fraction of the predicted frame duration and pulsing the backlight of the display for the first frame at a second time based on a difference between the predicted frame duration and the actual frame duration.
G09G 3/34 - Dispositions ou circuits de commande présentant un intérêt uniquement pour l'affichage utilisant des moyens de visualisation autres que les tubes à rayons cathodiques pour la présentation d'un ensemble de plusieurs caractères, p. ex. d'une page, en composant l'ensemble par combinaison d'éléments individuels disposés en matrice en commandant la lumière provenant d'une source indépendante
Apparatuses, systems, and techniques to perform a neural network to generate an image. In at least one embodiment, for example, one or more neural networks generate one or more portions of one or more images and one or more captions. In at least one embodiment, as another example, a processor uses one or more neural networks to generate one or more images from text based, at least in part, on one or more first images without text indicating content of one or more first images and one or more second images with text indicating content of one or more second images.
G06V 10/75 - Organisation de procédés de l’appariement, p. ex. comparaisons simultanées ou séquentielles des caractéristiques d’images ou de vidéosApproches-approximative-fine, p. ex. approches multi-échellesAppariement de motifs d’image ou de vidéoMesures de proximité dans les espaces de caractéristiques utilisant l’analyse de contexteSélection des dictionnaires
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
In managing a multiple threaded processing system, it can be difficult to store and commit each thread. To reduce the computing resources needed to manage the multiple threads, a linear autobatch buffer process can be utilized. As thread requests are received, an appropriate autobatch buffer can be identified. If the autobatch buffer is full, an increment can be used to select a different autobatch buffer as the active buffer. Once each thread in the autobatch buffer are committed and completed, the buffer can be retired. One thread in the buffer is designated the control thread and is responsible for controlling and retiring the buffer so that the other threads do not expend resources checking on the buffer status.
Apparatuses, systems, and techniques for multi-object tracking of partially occluded objects in a monitored environment are provided. A reference point of a first object in an environment is identified based on characteristics pertaining to the first object. A portion of the first object is occluded by a second object in the environment relative to a perspective of a camera component associated with a set of image frames depicting the first object and the second object. A set of coordinates of a multi-dimensional model for the first object is updated based on the identified reference point. The updated set of coordinates indicate a region of at least one of the set of image frames that include the occluded portion of the first object relative to the identified reference point. A location of the first object is tracked in the environment based on the updated set of coordinates of the multi-dimensional model.
G06V 20/52 - Activités de surveillance ou de suivi, p. ex. pour la reconnaissance d’objets suspects
G06T 7/70 - Détermination de la position ou de l'orientation des objets ou des caméras
G06V 10/26 - Segmentation de formes dans le champ d’imageDécoupage ou fusion d’éléments d’image visant à établir la région de motif, p. ex. techniques de regroupementDétection d’occlusion
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
49.
COHERENT THREE-DIMENSIONAL PORTRAIT RECONSTRUCTION VIA UNDISTORTING AND FUSING TRIPLANE REPRESENTATIONS
Systems and methods are disclosed that utilize a triplane fusion architecture that achieves both state-of-the-art three-dimensional (3D) reconstruction accuracy and temporal consistency. For instance, recognizing the need to maintain both coherent identity and dynamic per-frame appearance to enable the best possible realism, the triplane fusion architecture may include an undistorter that removes view-dependent distortions from the raw triplane by using the triplane prior as a reference and a fuser that fuses the triplanes together to recover the occluded areas in the input frame by incorporating features from the triplane prior that is lifted from the frontal reference image. By using the undistorter, the fuser, and a volume renderer, the triplane fusion architecture allows for reconstruction of 3D portrait models from a monocular video stream of a user, which may be useful in various applications including 3D telepresence.
G06T 17/20 - Description filaire, p. ex. polygonalisation ou tessellation
G06T 13/40 - Animation tridimensionnelle [3D] de personnages, p. ex. d’êtres humains, d’animaux ou d’êtres virtuels
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 40/16 - Visages humains, p. ex. parties du visage, croquis ou expressions
50.
SENSOR FUSION USING ULTRASONIC SENSORS FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
In various examples, techniques for sensor-fusion based object detection and/or free-space detection using ultrasonic sensors are described. Systems may receive sensor data generated using one or more types of sensors of a machine. In some examples, the systems may then process at least a portion of the sensor data to generate input data, where the input data represents one or more locations of one or more objects within an environment. The systems may then input at least a portion of the sensor data and/or at least a portion of the input data into one or more neural networks that are trained to output one or more maps or other output representations associated with the environment. In some examples, the map(s) may include a height, an occupancy, and/or height/occupancy map generated, e.g., from a birds-eye-view perspective. The machine may use these outputs to perform one or more operations.
G01S 15/931 - Systèmes sonar, spécialement adaptés à des applications spécifiques pour prévenir les collisions de véhicules terrestres
G01S 15/04 - Systèmes de détermination de la présence d'une cible
G01S 15/06 - Systèmes déterminant les données relatives à la position d'une cible
G01S 15/86 - Combinaisons de systèmes sonar avec des systèmes lidarCombinaisons de systèmes sonar avec des systèmes n'utilisant pas la réflexion des ondes
51.
HYBRID DIFFERENTIABLE RENDERING FOR LIGHT TRANSPORT SIMULATION SYSTEMS AND APPLICATIONS
In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.
In various examples, identifying occluded areas of environments for autonomous systems and applications is described herein. For instance, systems and methods described herein may process sensor data generated using one or more sensors of a machine to determine one or more areas of an environment that are occluded by at least a part of the machine. In some examples, determining the area(s) of the environment may be based at least on processing the sensor data using one or more machine learning models, processing the sensor data with respect to configuration data, and/or using any other technique. The systems and methods may then determine whether one or more objects are located within the occluded area(s) of the environment. Additionally, the systems and methods may then cause the machine to perform one or more operations based at least on whether the object(s) is located within the occluded area(s).
In various examples, segmented data storage and processing for autonomous and semi-autonomous systems and applications is described herein. For instance, systems and methods are described herein that segment an environment into various areas, where respective systems that are located within the individual areas are used to store and/or process data that is generated within the individual areas. For example, and for an area of the environment, one or more systems that are located within the area may receive instances of data that are generated using one or more machines navigating within the area. The system(s) may then be configured to process the instances of data, such as updating a map associated with the area using the instances of data. Additionally, in order to synchronize data processing between the systems, the systems may be configured to communicate with one another to at least replicate a portion of the data processing.
In various examples, segmented map creation for autonomous and semi-autonomous systems and applications is described herein. For instance, systems and methods described herein may segment a map into various portions, where the systems and methods then update the map based at least on the segmentation. For instance, based at least on receiving instances of data from machines navigating with an environment associated with the HD map, the instances of data may be associated with various portions of the map. Additionally, metrics associated with the portions of the map may be updated, such as by indicating the numbers of instances of data that are associated with the portions of the map. As such, when a metric associated with a portion of a map is satisfied, such as by reaching a threshold, the portion of the map may be updated without updating one or more other portions of the map.
In various examples, multiple stage map creations for autonomous and semi-autonomous systems and applications is described herein. For instance, systems and methods are described herein that update portions of a high-definition (HD) map in one or more stages in order to ensure that updates between different portions of the HD map are synchronized with respect to one another and/or ensure that updates to portions of the HD map are compatible with portions of the HD map that are not updated. In order to perform such processes, the systems and methods may determine to update one or more portions of the HD map. The systems and methods may use multiple states for the portion(s) when performing the updates, such as a first state (e.g., a locked state) when updating the portion(s) and a second state (e.g., an unlocked state) when not performing an update on the portion(s).
A circuit including at least one a bit-storing cell and a read latch coupled to the bit-storing cell via a read bitline includes a capacitive feedback loop between an output of the read latch and the read bitline to inject capacitive noise on the read line that mitigates the effects of a Miller capacitor in the read latch.
G11C 11/413 - Circuits auxiliaires, p. ex. pour l'adressage, le décodage, la commande, l'écriture, la lecture, la synchronisation ou la réduction de la consommation
G11C 5/06 - Dispositions pour interconnecter électriquement des éléments d'emmagasinage
G11C 5/10 - Dispositions pour interconnecter électriquement des éléments d'emmagasinage pour interconnecter des capacités
57.
AUTOMATIC OPTIMIZATION OF DATA PROCESSING PIPELINES USING MACHINE LEARNING
Approaches are disclosed that can automatically tune parameters in an application pipeline. An application pipeline and datasets with labels can be accepted as input. An application pipeline can include various modules and information such as their interconnections and a set of parameters to be tuned. The input data can be fed into a preprocessing module and then fed into a parameter search module, which can navigate through the parameter space and search for improved and/or optimal parameters. The search can progress to informed selections based on outcomes of previous evaluations. The parameters identified can be used by an execution module to execute the pipeline. The results produced can be evaluated by an evaluation module that condenses its findings into a single score, which is passed back to a parameter search module to inform the next round of parameter predictions. Such an iterative process can continue until certain criteria are met, with final output corresponding to a set of automatically tuned parameters.
One or more embodiments of the present disclosure relate to generation of map data. In these or other embodiments, the generation of the map data may include determining whether objects indicated by the sensor data are static objects or dynamic objects. Additionally or alternatively, sensor data may be removed or included in the map data based on determinations as to whether it corresponds to static objects or dynamic objects.
G01S 13/04 - Systèmes déterminant la présence d'une cible
B60W 40/10 - Calcul ou estimation des paramètres de fonctionnement pour les systèmes d'aide à la conduite de véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier liés au mouvement du véhicule
B60W 40/12 - Calcul ou estimation des paramètres de fonctionnement pour les systèmes d'aide à la conduite de véhicules routiers qui ne sont pas liés à la commande d'un sous-ensemble particulier liés à des paramètres du véhicule lui-même
B60W 60/00 - Systèmes d’aide à la conduite spécialement adaptés aux véhicules routiers autonomes
G01S 7/00 - Détails des systèmes correspondant aux groupes , ,
G01S 13/86 - Combinaisons de systèmes radar avec des systèmes autres que radar, p. ex. sonar, chercheur de direction
G01S 13/89 - Radar ou systèmes analogues, spécialement adaptés pour des applications spécifiques pour la cartographie ou la représentation
G01S 13/931 - Radar ou systèmes analogues, spécialement adaptés pour des applications spécifiques pour prévenir les collisions de véhicules terrestres
G01S 17/04 - Systèmes de détermination de la présence d'une cible
G01S 17/931 - Systèmes lidar, spécialement adaptés pour des applications spécifiques pour prévenir les collisions de véhicules terrestres
G06T 7/73 - Détermination de la position ou de l'orientation des objets ou des caméras utilisant des procédés basés sur les caractéristiques
G06V 10/26 - Segmentation de formes dans le champ d’imageDécoupage ou fusion d’éléments d’image visant à établir la région de motif, p. ex. techniques de regroupementDétection d’occlusion
G06V 10/28 - Quantification de l’image, p. ex. seuillage par histogramme visant à discriminer entre les formes d’arrière-plan et d’avant-plan
Apparatuses, systems, and techniques to use one or more neural networks with adjusted resolution information. In at least one embodiment, for example, one or more neural network low resolution encoders are trained to one or more higher resolutions. In at least one embodiment, as another example, a processor is to adjust a resolution of information to be used by one or more neural networks based, at least in part, on one or more performance metrics of one or more neural networks.
G06T 3/4046 - Changement d'échelle d’images complètes ou de parties d’image, p. ex. agrandissement ou rétrécissement utilisant des réseaux neuronaux
G06T 3/4007 - Changement d'échelle d’images complètes ou de parties d’image, p. ex. agrandissement ou rétrécissement basé sur l’interpolation, p. ex. interpolation bilinéaire
60.
USING LARGE LANGUAGE MODELS TO AUGMENT PERCEPTION DATA IN ENVIRONMENT RECONSTRUCTION SYSTEMS AND APPLICATIONS
Approaches presented herein provide for the use of language models to generate tokenized descriptions of physical environments. In at least one embodiment, sensor and/or observational data can be obtained for an environment and used to generate a set of perception data. The perception data can be analyzed, along with approximate positional data within the environment, to identify a set of aligned map data. The aligned map data and perception data can be provided as input to a trained language model, which can be trained to correlate and/or fuse the information to generate a single, consistent representation of the environment. The language model can output a tokenized description of the environment, which can be in a domain-specific language, that is a compact but robust textual description of the environment.
Apparatuses, systems, and techniques to retrieve a set of retrieved scenarios using at least one example scenario, to use at least one first neural network to combine at least the set of retrieved scenarios to obtain combined information, and to use at least one second neural network to infer a new scenario based at least in part on the combined information. In at least one embodiment, scenarios are retrieved from a set of real-world driving scenarios and the new scenario is used to generate a simulation of automobile traffic.
In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.
G05B 13/02 - Systèmes de commande adaptatifs, c.-à-d. systèmes se réglant eux-mêmes automatiquement pour obtenir un rendement optimal suivant un critère prédéterminé électriques
G06F 18/21 - Conception ou mise en place de systèmes ou de techniquesExtraction de caractéristiques dans l'espace des caractéristiquesSéparation aveugle de sources
G06T 11/20 - Traçage à partir d'éléments de base, p. ex. de lignes ou de cercles
G06V 10/26 - Segmentation de formes dans le champ d’imageDécoupage ou fusion d’éléments d’image visant à établir la région de motif, p. ex. techniques de regroupementDétection d’occlusion
G06V 10/34 - Lissage ou élagage de la formeOpérations morphologiquesSquelettisation
G06V 10/44 - Extraction de caractéristiques locales par analyse des parties du motif, p. ex. par détection d’arêtes, de contours, de boucles, d’angles, de barres ou d’intersectionsAnalyse de connectivité, p. ex. de composantes connectées
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/56 - Contexte ou environnement de l’image à l’extérieur d’un véhicule à partir de capteurs embarqués
G06V 30/19 - Reconnaissance utilisant des moyens électroniques
G06V 30/262 - Techniques de post-traitement, p. ex. correction des résultats de la reconnaissance utilisant l’analyse contextuelle, p. ex. le contexte lexical, syntaxique ou sémantique
63.
SENSOR CALIBRATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
In various examples, sensor configuration for autonomous or semi-autonomous systems and applications is described. Systems and methods are disclosed that may use image feature correspondences between camera images along with an assumption that image features are locally planar to determine parameters for calibrating an image sensor with a LiDAR sensor and/or another image sensor. In some examples, an optimization problem is constructed that attempts to minimize a geometric loss function, where the geometric loss function encodes the notion that corresponding image features are views of a same point on a locally planar surface (e.g., a surfel or mesh) that is constructed from LiDAR data generated using a LiDAR sensor. In some examples, performing such processes to determine the calibration parameters may remove structure estimation from the optimization problem.
A system that includes at least one multi-threaded processor forms a multitude of converged thread sub-groups from a main thread group, wherein each thread sub-group includes a common code block. A loop is configured to jump to a different target address of a branch instruction in an order determined by a priority configured for each different target address.
Silicon photonic chips with embedded lasers and methods for manufacturing silicon photonic chips with embedded lasers are described herein. Some embodiments of the present invention may be directed to a silicon photonic chip including a laser disposed in the silicon photonic chip between a first and second surface of the silicon photonic chip. The laser may include an anode and a cathode each extending substantially parallel to at least one of the first or second surface through at least a portion of the silicon photonic chip. The silicon photonic chip may include a first through-dielectric via electrically connecting the anode to the second surface of the silicon photonic chip and a second through-dielectric via electrically connecting the cathode to the second surface of the silicon photonic chip.
H01S 5/026 - Composants intégrés monolithiques, p. ex. guides d'ondes, photodétecteurs de surveillance ou dispositifs d'attaque
H01S 5/32 - Structure ou forme de la région activeMatériaux pour la région active comprenant des jonctions PN, p. ex. hétérostructures ou doubles hétérostructures
The present disclosure relates to executing a first task of an application over one or more first execution iterations to generate one or more first data iterations of first data. At least one individual first timestamp may respectively correspond to at least one first data iterations of the one or more first data iterations. A second task may be executed to generate one or more second data iterations based at least on the at least one first data iteration, the second task obtaining the at least one individual first timestamp corresponding to the at least one first data iteration. In some embodiments, the at least one first data iteration for use may be selected based at least on the corresponding at least one first timestamp.
Apparatuses, systems, and techniques to determine that a first image and a second image generated by an image sensor are images of a same static scene; and determine that a noise estimate for the image sensor based at least on a difference between first values of a first subset of pixels of the first image and second values of a corresponding second subset of pixels of the second image.
G06V 10/98 - Détection ou correction d’erreurs, p. ex. en effectuant une deuxième exploration du motif ou par intervention humaineÉvaluation de la qualité des motifs acquis
H04N 17/00 - Diagnostic, test ou mesure, ou leurs détails, pour les systèmes de télévision
H04N 23/60 - Commande des caméras ou des modules de caméras
68.
ACCELERATED DATA DECOMPRESSION USING PARALLEL PROCESSORS
In various examples, a GPU may be equipped with specialized or dedicated hardware (e.g., a copy engine) customized for sliding window dictionary-based (e.g., Snappy) decompression. As such, data that was compressed using some unsupported compression format (e.g., Zstandard) may be transcoded to a supported compression format (e.g., Snappy) and decompressed in the supported format. In some embodiments, one or more entropy decoding operations (e.g., Huffman decoding, ANS decoding) and/or transcoding into a supported compression format (e.g., Snappy) may be executed on general-purpose hardware on a GPU (e.g., a SM) using GPU-accelerated computing (e.g., CUDA) software, and decompression may be executed on the GPU on specialized or dedicated hardware (e.g., a copy engine) customized for decompressing the supported compression format. In some embodiments, similar computations common to Huffman, extra bit, ANS, and/or other types of decoding operations may be parallelized (e.g., on a streaming multiprocessor of a GPU).
Disclosed are systems and techniques for parallel deterministic stochastic rounding. In one embodiment, the techniques include obtaining a first set of values of a first bit-length and a second set of values of the first bit-length and generating a third set of values of a second bit-length. Each value of the third set of values is a lower precision value of a corresponding value of the first set of values. The techniques include generating a fourth set of values of the second bit-length, and each value of the fourth set of values is a lower precision value of a corresponding value of the second set of values. Generating the third set of values and the fourth set of values is performed in parallel.
Statistical analysis can be used to attempt to identify potentially malicious references, such as trap URLs. When a URL is utilized for a request, that request can be intercepted before analysis before that URL is resolved to an address. Portions of this URL, as well as the entire URL, can be compared against one or more lists of known URLs using a probabilistic matching process to determine whether there are any matches that are very close but not quite exact. Any determined match with high probability above a suspicion threshold can be flagged as being suspicious, or associated with a potentially malicious site. An action can then be taken, such as to block that URL or prompt a user for confirmation of intent.
G06F 16/955 - Recherche dans le Web utilisant des identifiants d’information, p. ex. des localisateurs uniformisés de ressources [uniform resource locators - URL]
Apparatuses, systems, and techniques for streaming data to client devices using a data processing unit (DPU) or other Peripheral Component Interconnect Express (PCIe) device. One computing system includes a central processing unit (CPU), a first PCIe device, a second PCIe device, and a hardware synchronization mechanism to synchronize streaming data from the first PCIe device to the second PCIe device without involvement by the CPU.
G06F 13/42 - Protocole de transfert pour bus, p. ex. liaisonSynchronisation
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
Applications written in memory unsafe languages, such as C, C++, and CUDA, are vulnerable to a variety of memory safety errors because they do not validate the bounds and lifetime of memory accesses. For example, spatial memory safety errors occur when a pointer is used to access an object beyond its intended bounds while temporal memory safety errors occur when a pointer is used to access an object beyond its lifetime. Memory safety errors can lead to control-flow hijacking, silent data corruption, difficult-to-diagnose crashes, and security exploitation. Unfortunately, existing software-based solutions either provide low error detection coverage or come with significant runtime overheads, and existing hardware-accelerated GPU-based solutions have poor scalability or intrusive hardware changes. The present disclosure provides memory safety using a combination of hardware and software.
G06F 21/78 - Protection de composants spécifiques internes ou périphériques, où la protection d'un composant mène à la protection de tout le calculateur pour assurer la sécurité du stockage de données
73.
LANGUAGE INSTRUCTED TEMPORAL LOCALIZATION IN VIDEOS
Embodiments of the present disclosure relate to language instructed temporal localization in videos, and provide multimodal large language models (LLMs) for performing language instructed temporal localization in video, as well as methods for training and implementing such models. In contrast to conventional systems, models according to embodiments of the present disclosure are designed to answer “when?” questions, while simultaneously improving other relevant capabilities of multimodal LLMs.
Systems and methods for generating a representative value of a data set by first compressing a portion of values in the data set to determine a first common value and further compressing a subset of the portion of values to determine a second common value. The representative value is generated by taking the difference between the first common value and the second common value, wherein the representative value corresponds to a mathematical relationship between the first and second common values and each value within the subset of the portion of values. The representative value requires less storage than the first and second common values.
G06F 7/57 - Unités arithmétiques et logiques [UAL], c.-à-d. dispositions ou dispositifs pour accomplir plusieurs des opérations couvertes par les groupes ou pour accomplir des opérations logiques
View synthesis is a computer graphics process that generates a new image of a scene from a novel (previously unseen) viewpoint of the scene. Typically, the graphics process relies on a machine learning model that has been trained with ground truth pose information. Since ground truth pose information is not readily available, some solutions rely on a Structure-from-Motion (SfM) library COLMAP to generate pose information for a given image. However, this pre-processing step is not only time-consuming but also can fail due to its sensitivity to feature extraction errors and difficulties in handling texture-less or repetitive regions. The present disclosure provides view synthesis from learned camera poses without relying on SfM pre-processing.
In various examples, audio alerts of emergency response vehicles may be detected and classified using audio captured by microphones of an autonomous or semi-autonomous machine in order to identify travel directions, locations, and/or types of emergency response vehicles in the environment. For example, a plurality of microphone arrays may be disposed on an autonomous or semi-autonomous machine and used to generate audio signals corresponding to sounds in the environment. These audio signals may be processed to determine a location and/or direction of travel of an emergency response vehicle (e.g., using triangulation). Additionally, to identify siren types—and thus emergency response vehicle types corresponding thereto—the audio signals may be used to generate representations of a frequency spectrum that may be processed using a deep neural network (DNN) that outputs probabilities of alert types being represented by the audio data.
G08G 1/0965 - Dispositions pour donner des instructions variables pour le trafic avec un indicateur monté à l'intérieur du véhicule, p. ex. délivrant des messages vocaux répondant à des signaux provenant d'un autre véhicule, p. ex. d'un véhicule de secours
G08G 1/0967 - Systèmes impliquant la transmission d'informations pour les grands axes de circulation, p. ex. conditions météorologiques, limites de vitesse
Apparatuses, systems, and techniques to perform parallel processing. In at least one embodiment, a parallel processing algorithm for performing an additive prefix scan is selected from a plurality of alternatives based on an arrangement of a group of threads provided to perform the scan.
In various examples, a technique for slot filling includes receiving a natural language sentence from a user and identifying a first mention span included in the natural language sentence. The technique also includes determining, using a first machine learning model, that the first mention span is associated with a first slot class included in a set of slot classes based on a set of slot class descriptions corresponding to the set of slot classes.
Apparatuses, systems, and techniques to determine a matrix multiplication algorithm for a matrix multiplication operation. In at least one embodiment, a matrix multiplication operation is analyzed to determine an appropriate matrix multiplication algorithm to perform the matrix multiplication algorithm.
Disclosed are apparatuses, systems, and techniques that evaluate suitability of prompts for language model (LM) processing for improved quality and security of LM outputs. The techniques include determining prompt verification score(s) that include a first subset of tokens and a second subset of tokens, and obtaining, using an LM, the individual prompt verification score characterizing a likelihood that the second subset of tokens occurs, in the prompt, together with the first subset of tokens. The techniques further include determining, using the prompt verification score(s), whether the prompt is to be provided to the LM.
In various examples, systems and methods are disclosed relating to generating realistic and diverse simulated scenes of people for updating/training artificial intelligence models. A configuration file can be received that that specifies randomization for a semantic layer of a model for a scene. A distribution can be sampled according to the randomization to select data for the semantic layer of the model. The scene can be generated to include the model having the data selected for the semantic layer. The scene, including the model, can be rendered to generate an image for updating a neural network.
G06T 19/20 - Édition d'images tridimensionnelles [3D], p. ex. modification de formes ou de couleurs, alignement d'objets ou positionnements de parties
G06T 7/70 - Détermination de la position ou de l'orientation des objets ou des caméras
G06T 13/40 - Animation tridimensionnelle [3D] de personnages, p. ex. d’êtres humains, d’animaux ou d’êtres virtuels
G06V 10/60 - Extraction de caractéristiques d’images ou de vidéos relative aux propriétés luminescentes, p. ex. utilisant un modèle de réflectance ou d’éclairage
G06V 20/70 - Étiquetage du contenu de scène, p. ex. en tirant des représentations syntaxiques ou sémantiques
82.
REASSIGNING A NETWORK ADDRESS OF A DISTRIBUTED UNIT
Apparatuses, systems, and techniques to perform dynamic mapping between one or more Open Radio Access Network (O-RAN) radio units (RUs) and one or more O-RAN distributed units (DUs). For example, processors or computing systems to perform switching of mappings between open radio unit (O-RU) and open distributed unit (O-DU) in an open radio access network (O-RAN). In at least one embodiment, a processor including circuitry performs a program to cause reassigning of mappings between radio unit (RUs) and distributed unit (DUs) without the need of restarting or reconfiguration of RUs and/or DUs in an O-RAN network.
Apparatuses, systems, and techniques that utilize a neural network to jointly infer signal parameters to direct and transmit wireless signals. In at least one embodiment, one or more neural networks are trained, using reinforcement learning techniques, to infer hybrid beamforming parameters used by one or more devices to transmit wireless signals.
H04B 7/06 - Systèmes de diversitéSystèmes à plusieurs antennes, c.-à-d. émission ou réception utilisant plusieurs antennes utilisant plusieurs antennes indépendantes espacées à la station d'émission
84.
SIGNAL PROCESSING TECHNIQUE USING SIGNAL INFORMATION
Apparatuses, systems, and techniques that utilize a neural network to infer signal parameters to direct and transmit wireless signals. In at least one embodiment, one or more neural networks are trained, using reinforcement learning techniques, to infer a beam direction to be used by a first device to transmit a signal based, at least in part, on characteristics of another signal being transmitted by a second device.
H04B 7/06 - Systèmes de diversitéSystèmes à plusieurs antennes, c.-à-d. émission ou réception utilisant plusieurs antennes utilisant plusieurs antennes indépendantes espacées à la station d'émission
A text-to-image machine learning model takes a user input text and generates an image matching the given description. As an extension to this concept, text-to-3D content models can take a user input text to generate a 3D content. However, existing text-to-3D content models require different views to be individually generated and optimized in order to form the content in 3D, which is costly in terms of computation and time, and are typically limited to the generation of 3D objects as opposed to large 3D scenes. The present description enables the creation of 3D scenes in a less costly manner by using a feed-forward neural network that can generate a 3D representation of a scene from a plurality of labeled voxels that describe the scene in 3D.
G06V 10/771 - Sélection de caractéristiques, p. ex. sélection des caractéristiques représentatives à partir d’un espace multidimensionnel de caractéristiques
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
Apparatuses, systems, and techniques to identify instructions for advanced execution. In at least one embodiment, a processor performs one or more instructions that have been identified by a compiler to be speculatively performed in parallel.
Metadata generally refers to data that describes, or gives information about, other data. Metadata can be used for a wide variety of purposes, including for ensuring the safety of memory accesses. For example, to prevent memory safety errors, metadata, which indicates the base address and size of the data, can be used to validate memory access requests as prerequisite to allowing the memory access. While there are many useful applications of metadata, including for memory safety as mentioned above, the underlying metadata storage and retrieval processes that have been developed to date suffer from various problems. The present disclosure provides an object-level metadata locator, which can allow for an internal object layout to be maintained and which can scale to an arbitrary number of objects while requiring lower memory overhead than that required in the prior art.
In examples, when attempting to interpolate or extrapolate a frame based on motion vectors of two adjacent frames, there can be more than one pixel value mapped to a given location in the frame. To select between conflicting pixel values for the given location, similarities between the motion vectors of source pixels that cause the conflict and global flow may be evaluated. For example, a level of similarity for a motion vector may be computed using a similarity metric based at least on a difference between an angle of a global motion vector and an angle of the motion vector. The similarity metric may also be based at least on a difference between a magnitude of the global motion vector and a magnitude of the motion vector. The similarity metric may weigh the difference between the angles in proportion to the magnitude of the global motion vector.
A request is received for a virtual asset of a virtual asset data store for inclusion in a virtual scene. The request includes first characteristic data including characteristics associated with the requested virtual asset. One or more virtual assets of the virtual asset data store are associated with tags obtained from an output of an artificial intelligence (AI) model. Tags are obtained for the requested virtual asset based on the first characteristic data and second characteristic data associated with an additional virtual asset of the virtual scene. A determination is made, based on tags for virtual assets of the virtual data store, of whether the virtual asset data store identifies a virtual asset that satisfies criteria with respect to the obtained tags for the requested asset. Upon determining that the criteria are satisfied, the virtual asset is provided for inclusion in the virtual scene in accordance with the request.
In various examples, one or more of the embodiments apply an iterative curve-closing process to disjointed navigable path data to derive a closed navigable bounds curve that may be used to define a drivable surface within a simulated driving environment. The navigable bounds may be used to create accurate driving simulations and/or to create rendering simulations by providing a closed bounds from which a road surface topology can be built, and/or other drivable surfaces. Internal closed curves may be generated within the navigable bounds to define non-drivable regions or traffic islands, such as curbs, medians, or other non-drivable regions. The non-drivable area within interior closed curves may be subtracted from the area within a navigable bounds closed curve to derive a net drivable area that includes both structured and unstructured drivable surfaces.
An optical transmitter includes lasers configured to generate a wave division multiplex (WDM) on a light guide, and a Code Division Multiple Access (CDMA) symbol generator coupled to modulate CDMA symbols on the light guide across the channels of the WDM. The transmitter utilizes of laser locking controls configured to correlate the CDMA symbols to frequency adjustments applied to the lasers.
Optical circuit architectures utilizing primary laser light sources and at least one auxiliary laser light source. The primary lasers may be fixed-wavelength lasers and/or comb lasers, and the auxiliary lasers may be fixed-wavelength lasers, tunable-wavelength lasers, and/or comb lasers. In some cases optical switches are utilized along the optical paths in various configurations between the laser inputs and output terminals of the optical paths or between the laser inputs and a transform network.
Technologies directed to allocating and reallocating phases across independent voltage rails for multiple circuits are described. A multi-phase voltage regulator (VR) module with multiple output rails can include multiple VR controllers, multiple phases, an output switch matrix, and phase allocation logic. The phase allocation logic, using the output switch matrix, can selectively allocate and reallocate any combination of the multiple phases to one of the multiple VR controllers to provide an output power on one of the multiple output rails.
Simulation of complex agents, such as robots with many articulation links, can be performed utilizing a pre-computed a response matrix for each link. When an impulse is applied to a link for this agent, the response matrix for a root node can be used to determine an impact of that impulse on the root node, as well as changes in velocity for any direct child node. This process can be performed recursively for each link down to the leaf links of a hierarchical agent structure. These response matrices can be solved recursively from root to leaf while only visiting each hierarchical link once. Such an approach can be used to solve a full set of constraints acting on the agent in an amount of time per solver iteration that is on the order of the number of links, or O(N) time per solver iteration.
G06F 30/27 - Optimisation, vérification ou simulation de l’objet conçu utilisant l’apprentissage automatique, p. ex. l’intelligence artificielle, les réseaux neuronaux, les machines à support de vecteur [MSV] ou l’apprentissage d’un modèle
In various examples, systems and methods are disclosed relating to generation of four-dimensional (4D) content models, such as 4D content models to render realistic sequences of frames of 3D data. The systems can initialize a 3D component of the 4D content model, such as a 3D Gaussian splatting representation, based at least on a prompt for the 4D content. The system can configure motion and/or dynamics for the sequence of frames by evaluating frames rendered from the 4D content model using one or more latent diffusion models (LDMs), including a video LDM. The system can perform operations such as autoregressive generation of frames to create long sequences of content, motion amplification to facilitate realistic, dynamic motion generation, and regularization to facilitate generation of complex dynamics.
In various examples, an interactive agent platform that hosts development and/or deployment of an interactive agent may provide an interpreter or compiler that interprets or executes code written in the interaction modeling language, and a designer may provide customized code written in the interaction modeling language for the interpreter to execute. The interaction modeling language may be used to define a flow of interactions that instruct the interpreter what actions or events to generate in response to a sequence of detected and/or executed human-machine interactions. The interaction categorization schema may classify interactions by standardized interaction modality and/or corresponding standardized action category. As such, a flow may be used to model an agent intent or inferred user intent, which a designer may use to build more complex interaction patterns with the interactive agent.
H04L 51/02 - Messagerie d'utilisateur à utilisateur dans des réseaux à commutation de paquets, transmise selon des protocoles de stockage et de retransmission ou en temps réel, p. ex. courriel en utilisant des réactions automatiques ou la délégation par l’utilisateur, p. ex. des réponses automatiques ou des messages générés par un agent conversationnel
H04L 51/216 - Gestion de l'historique des conversations, p. ex. regroupement de messages dans des sessions ou des fils de conversation
98.
BACKCHANNELING FOR INTERACTIVE SYSTEMS AND APPLICATIONS
In various examples, an interactive agent platform that hosts development and/or deployment of an interactive agent such as a digital avatar may employ backchanneling to provide feedback to the user while the user is talking or doing something detectable. For example, backchanneling may be implemented by triggering interactive agent postures (e.g., based on whether the user or the avatar is speaking, or based on the interactive agent waiting for a response from the user), short vocal bursts like “yes”, “aha”, or “hmm” while the user is talking (e.g., signaling to the user that the interactive agent is listening), gestures (e.g., shaking the interactive's agent's head), and/or otherwise. As such, a designer may specify various backchanneling techniques that make conversations with an interactive agent feel more natural.
In various examples, an interactive agent platform that hosts an interactive agent may represent and/or communicate human-machine interactions and related events using a standardized interaction modeling API and/or an event-driven architecture. In an example implementation, a standardized interaction modeling API serves as a common protocol in which components use a standardized interaction categorization schema to represent all activities by agents and users as actions in a standardized form, represent states of multimodal actions from users and agents as events in a standardized form, implement standardized mutually exclusive modalities that define how conflicts between standardized categories of actions are resolved (e.g. saying two things at the same time is not possible, while saying something and making a gesture at the same time may be possible), and/or implement standardized protocols for any number of standardized modalities and actions independent of implementation.
G06F 16/21 - Conception, administration ou maintenance des bases de données
G06F 40/58 - Utilisation de traduction automatisée, p. ex. pour recherches multilingues, pour fournir aux dispositifs clients une traduction effectuée par le serveur ou pour la traduction en temps réel
100.
DEPLOYMENT OF INTERACTIVE SYSTEMS AND APPLICATIONS USING LANGUAGE MODELS
In various examples, an interactive agent platform that hosts development and/or deployment of an interactive agent may use an interaction modeling language and corresponding interpreter that support the use of natural language descriptions and one or more LLMs to facilitate the development and deployment of more complex and nuanced human-machine interactions. For example, the interpreter may prompt an LLM to generate a natural language description of one or more instruction lines defining a flow, generate one or more instruction lines for a specified flow, determine whether an event matches a flow description of an active flow, determine whether an unmatched event matches the name and/or instruction(s) of an active flow, generate a flow in response to an unmatched event, and/or otherwise.
