Abstract: An auxiliary lipid-lowering Camellia diacylglycerol edible oil and a preparation method thereof, involving grinding walnuts, peas, and sweet corn kernels, then thorough enzymatic hydrolysis; the obtained nutritious rapeseed oil is dispersed in the mixed edible oil, the prepared nutritious Camellia diacylglycerol oil mixture contains rich nutrients; the plant extract obtained by ultrasonic extraction is effectively adsorbed by the mixed colloid, the obtained nanoparticles that assist in lowering blood lipids and promoting metabolism cooperate with the nutritious Camellia diacylglycerol oil mixture to have an effective lipid-lowering effect; the antioxidant stabilizing composition and the nanoparticles that assist in lowering blood lipids and promoting metabolism are dispersed in the nutritious Camellia diacylglycerol oil mixture; the prepared auxiliary lipid-lowering Camellia diacylglycerol edible oil is rich in nutrition, does not increase blood lipids in the body after long-term consumption, doesn't cause da

Abstract: A high-bioactivity goat colostrum composite freeze-dried powder relates to the technical field of food, comprising the following components in parts by weight: 60-70 parts of goat colostrum powder, 5-8 parts of composite probiotic liposome freeze-dried powder, and 6-9 parts of mannose oligosaccharides; the composite probiotic liposome freeze-dried powder is prepared from the following components: gallic acid, phytosterol, soybean phosphatidylcholine, modified chitosan, and probiotic powder; the probiotic powder is Bifidobacterium longum powder or Lactobacillus acidophilus powder.

Abstract: A method for generating output using multiple large language models (LLMs) including at least one expert model and a plurality of draft models is disclosed. A selection policy that is configured to select, for each of the at least one expert model, a draft model that is maximally aligned with the expert model is trained. The policy is trained using a training dataset comprising inputs from multiple contexts. Upon receiving a first user input, a pair of expert and draft models for processing the first user input using the trained policy is determined. The output is generated using the determined pair of models.

Abstract: Methods and systems for retrieving relevant information in response to an input question. The method includes obtaining text content related to the input question and partitioning the content into one or more paragraphs based on predefined rules. The method further involves extracting one or more evidence spans that are relevant to the input question by inputting the text content and the question into a trained language model. A semantic search is then performed on both the paragraphs and the extracted evidence spans, ranking the candidate passages based on their relevance to the input question. Each candidate passage may comprise either a paragraph or an evidence span that addresses the question. The disclosed methods and systems improve the quality and relevance of retrieved information by combining heuristic-based content partitioning with machine learning-based evidence extraction.

Abstract: A computerized method for generating an answer to an input question, the method has the steps of: identifying, in a knowledge graph (KG), one or more entities included in the input question; finding, in the KG, a plurality of reasoning paths for the one or more entities based on comparison of a similarity between an embedding of each of the plurality of reasoning paths and an embedding of the input question; retrieving a plurality of quotes from a network, each quote being a piece of text related to the input question taken verbatim from the network; and sending the input question, and an input set to a foundation model (FM) to obtain the answer, the input set comprising the plurality of reasoning paths and the plurality of quotes.

Abstract: A computerized method has the steps of: generating one or more queries from an input question; generating one or more outputs; and outputting an answer based on the one or more outputs. Said generating the one or more outputs has the steps of: for each query, forming a reasoning tree with the query being a root node and a current node, generating one or more candidates as leaf nodes of the current node, by inputting a reasoning path from the root node to the current node into a foundation model, searching the reasoning tree using an artificial intelligence model to select a leaf node as the current node, and repeating said generating the one or more candidate nodes and said searching the reasoning tree until a termination condition is met, and using an updated reasoning path from the root node to the current node as the output for the query.

Abstract: Post-training quantization of Large Language Models and other neural networks. A plurality of quantization iterations are applied during which each of the linear network layers of a block are processed as follows: a respective approximated Hessian matrix is computed for the linear network layer using a set of layer-specific network weights for the linear network layer as computed in a preceding quantization iteration and sets of layer-specific network weights for each of the remaining linear network layers set to the values of such weights prior to the preceding quantization iteration; then an updated set of quantized set of layer-specific network weights for the linear network layer is computed based on the respective approximated Hessian matrix for the linear network layer. The updated quantized sets of layer-specific network weights computed in a final quantization iteration are stored as a final quantized set of parameters for the block.

Abstract: A method and an apparatus for storing data points are provided. The method comprises: receiving the plurality of data points, each data point of the plurality of data points being represented in a floating-point representation; quantizing each one of the first plurality of data points, by: executing, during a first quantization phase: converting each data point of the plurality of data points into a corresponding first data point of a plurality of first data points; executing, during a second quantization phase: applying, to each first data point of the plurality of first data points a clamping function, thereby converting each first data point of the plurality of first data points into a corresponding second data point of a plurality of second data points; and storing the plurality of second points for further calculations instead of the first plurality of data points.

Abstract: Systems and methods for computing a neural network layer of a neural network are described. A float shift inner product operator is described for computing an inner product between a floating point input vector and a weight vector having weight values that are power of two values. An inner product is computed by performing addition on the sign bits and exponent bits of a floating point input element and corresponding weight element.

Abstract: Methods and processors for using a Neural Network (NN) are disclosed. The method includes, during a first iteration, determining a first sub-network of the NN and training the first sub-network. The method includes during a second iteration a second sub-network of the NN and training the second sub-network. The method includes during an inference iteration of the NN, selecting a target sub-network amongst the first sub-network and the second sub-network, and generating an inference output by employing only the target sub-network of the NN on inference data for reducing computational resources of the processor for generating the inference output.