Abstract: The invention relates to an inhibitory chimeric antigen receptor (N-CAR) comprising an extracellular domain comprising an antigen binding domain, a transmembrane domain and, an intracellular domain wherein the intracellular domain comprises an Immunoreceptor Tyrosine-based Switch Motif ITSM, wherein said ITSM is a sequence of amino acid TX1YX2X3X4, wherein X1 is an amino acid X2 is an amino acid X3 is an amino acid and X4 is V or I.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment. In one aspect, a method comprises: receiving a natural language text sequence that characterizes a task to be performed by the agent in the environment; generating an encoded representation of the natural language text sequence; and at each of a plurality of time steps: obtaining an observation image characterizing a state of the environment at the time step; processing the observation image to generate an encoded representation of the observation image; generating a sequence of input tokens; processing the sequence of input tokens to generate a policy output that defines an action to be performed by the agent in response to the observation image; selecting an action to be performed by the agent using the policy output; and causing the agent to perform the selected action.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. In one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. In one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. In one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an optical flow label from a lidar point cloud. One of the methods includes obtaining data specifying a training example, including a first image of a scene in an environment captured at a first time point and a second image of the scene in the environment captured at a second time point. For each of a plurality of lidar points, a respective second corresponding pixel in the second image is obtained and a respective velocity estimate for the lidar point at the second time point is obtained. A respective first corresponding pixel in the first image is determined using the velocity estimate for the lidar point. A proxy optical flow ground truth for the training example is generated based on an estimate of optical flow of the pixel between the first and second images.

Abstract: A method includes obtaining first feature vectors and second feature vectors representing contents of a first and second image frame, respectively, of an input video. The method may also include generating, based on the first feature vectors, first slot vectors, where each slot vector represents attributes of a corresponding entity as represented in the first image frame, and generating, based on the first slot vectors, predicted slot vectors including a corresponding predicted slot vector that represents a transition of the attributes of the corresponding entity from the first to the second image frame. The method may additionally include generating, based on the predicted slot vectors and the second feature vectors, second slot vectors including a corresponding slot vector that represents the attributes of the corresponding entity as represented in the second image frame, and determining an output based on the predicted slot vectors or the second slot vectors.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to predict optical flow. One of the methods includes obtaining a batch of one or more training image pairs; for each of the pairs: processing the first training image and the second training image using the neural network to generate a final optical flow estimate; generating a cropped final optical flow estimate from the final optical flow estimate; and training the neural network using the cropped optical flow estimate.

Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: A system and method for generating impact information based on likelihood of component defect occurrence determination is provided. In one embodiment, the system includes one or more physical processors configured by machine-readable instructions to: obtain supply chain information for a component acquired by a user from a supplier; determine a likelihood of component defect occurrence based on the supply chain information, the defect likelihood reflecting the likelihood of defect occurrence for the component; identify devices that use the component having the likelihood of component defect; and effectuate presentation of the identified devices as an interactive information map.

Abstract: A tool is provided for connecting and disconnecting links of a conveyor chain. The tool includes a base, a chain guide plate mounted on the base for supporting a length of conveyor chain in a fixed position relative to the base, and a backup block carried on the base. A pin extraction/insertion block is positioned on the base with the chain guide plate positioned between the backup block and the pin extraction/insertion block. A ram is carried on the pin extraction/insertion block for extracting a pin from a position in aligned holes in adjacent links while the chain is held in its fixed position, and an insertion rod is carried on the pin extraction/insertion block for inserting a pin in aligned holes in adjacent links.

Abstract: A tool is provided for connecting and disconnecting links of a conveyor chain. The tool includes a base, a chain guide plate mounted on the base for supporting a length of conveyor chain in a fixed position relative to the base, and a backup block carried on the base. A pin extraction/insertion block is positioned on the base with the chain guide plate positioned between the backup block and the pin extraction/insertion block. A ram is carried on the pin extraction/insertion block for extracting a pin from a position in aligned holes in adjacent links while the chain is held in its fixed position, and an insertion rod is carried on the pin extraction/insertion block for inserting a pin in aligned holes in adjacent links.

Abstract: A method for repeated emphasis of a component in a user interface may include selecting, by a processor, at least one component in a user interface for target emphasis for performance of a repeated emphasis. The method may also include performing, by the processor, the repeated emphasis on the at least one selected component. Performing the repeated emphasis may include automatically, repeatedly performing an action associated with the selected component without a user input, wherein each action would require the user input without the repeated emphasis being performed.

Abstract: Disclosed is a multi-link conveyor that includes nestable end protector links that capture and retain link pins. The end protector link includes a first link segment having an outer wall, a non-circular bore having a cross-section larger than a cross-section of one of the pins, a circular counterbore connected to the non-circular bore and having a diameter larger than the head of one of the pins, and a circular countersink connected to the counterbore and having a first diameter that equals the diameter of the counterbore and a second diameter, flush with the outer wall, having a diameter larger than the first diameter. The end protector link includes a second link segment, adapted to nest with the first link segment of another end protector link, having an outer wall in a second vertical plane and a flush non-circular bore extending perpendicularly through the outer wall.

Abstract: Disclosed is a multi-link conveyor that includes nestable end protector links that capture and retain link pins. The end protector link includes a first link segment having an outer wall, a non-circular bore having a cross-section larger than a cross-section of one of the pins, a circular counterbore connected to the non-circular bore and having a diameter larger than the head of one of the pins, and a circular countersink connected to the counterbore and having a first diameter that equals the diameter of the counterbore and a second diameter, flush with the outer wall, having a diameter larger than the first diameter. The end protector link includes a second link segment, adapted to nest with the first link segment of another end protector link, having an outer wall in a second vertical plane and a flush non-circular bore extending perpendicularly through the outer wall.