DeepMind Technologies Limited patent applications on 2025-06-05

Patent Applications by DeepMind Technologies Limited on June 5th, 2025

DeepMind Technologies Limited: 5 patent applications

DeepMind Technologies Limited has applied for patents in the areas of G06F8/35 (model driven, 1), G06F30/27 (using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model, 1), G06N3/04 (Architecture, e.g. interconnection topology, 1), G06V10/462 (IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING, 1), G06V10/774 (IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING, 1)

With keywords such as: computer, programs, methods, systems, apparatus, including, encoded, storage, media, generating in patent application abstracts.

Top Inventors:

• Rémi Leblond of Cachan FR (1 patents)
• Alaa Saade of Montreuil FR (1 patents)
• Corentin Tallec of Paris FR (1 patents)
• Felix Axel Gimeno Gil of London GB (1 patents)
• Florent Altché of Paris FR (1 patents)

Patent Applications by DeepMind Technologies Limited

20250181325. COMPUTER CODE GENERATION TASK DESCRIPTIONS USING NEURAL NETWORKS (DeepMind Technologies Limited)

Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating computer code using neural networks. one of the methods includes receiving data describing a computer programming task; generating a plurality of candidate computer programs by sampling a plurality of output sequences from a set of one or more generative neural networks; clustering the plurality of candidate computer programs; for each cluster in a set of the clusters: processing each of the respective plurality of candidate computer programs in the cluster using a correctness estimation neural network to generate a correctness score for the candidate computer program; and selecting a representative computer program for the cluster using the correctness scores for the respective plurality of candidate computer programs in the cluster; and selecting one or more of the representative computer programs for the clusters as synthesized computer programs for performing the computer programming task.

20250181803. SIMULATING PHYSICAL ENVIRONMENTS USING FINE-RESOLUTION COARSE-RESOLUTION MESHES (DeepMind Technologies Limited)

Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for simulating a state of a physical environment. in one aspect, a method performed by one or more computers for simulating the state of the physical environment is provided. the method includes, for each of multiple time steps: obtaining data defining a fine-resolution mesh and a coarse-resolution mesh that each characterize the state of the physical environment at the current time step, where the fine-resolution mesh has a higher resolution than the coarse-resolution mesh; processing data defining the fine-resolution mesh and the coarse-resolution mesh using a graph neural network that includes: (i) one or more fine-resolution update blocks, (ii) one or more coarse-resolution update blocks, and (iii) one or more up-sampling update blocks; and determining the state of the physical environment at a next time step using updated node embeddings for nodes in the fine-resolution mesh.

20250181887. PROCESSING NETWORK INPUTS USING PARTITIONED ATTENTION (DeepMind Technologies Limited)

Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing network inputs using a neural network that implements partitioned attention.

20250182439. UNSUPERVISED LEARNING OBJECT KEYPOINT LOCATIONS IMAGES THROUGH TEMPORAL TRANSPORT OR SPATIO-TEMPORAL TRANSPORT (DeepMind Technologies Limited)

Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for unsupervised learning of object keypoint locations in images. in particular, a keypoint extraction machine learning model having a plurality of keypoint model parameters is trained to receive an input image and to process the input image in accordance with the keypoint model parameters to generate a plurality of keypoint locations in the input image. the machine learning model is trained using either temporal transport or spatio-temporal transport.

20250182453. GENERATING COMPRESSED REPRESENTATIONS VIDEO EFFICIENT LEARNING VIDEO TASKS (DeepMind Technologies Limited)

Abstract: a method is proposed to train an adaptive system to perform a video processing task, based on a database of compressed representations of video data items. the compressed representations were generated by a trained adaptive compressor unit.