Abstract: A thin film transistor comprises: an active layer; a gate insulating film on the active layer, a gate electrode at least partially overlapping the active layer, and a source electrode and a drain electrode connected to the active layer and spaced apart from each other, wherein the drain electrode and the gate electrode are formed integrally, the gate insulating film includes a first gate insulating film overlapping the gate electrode, and the drain electrode contacts the active layer along a side surface of the first gate insulating film.

Abstract: Provided are a multi-modal chatting apparatus and method which automatically generate and present a picture related to a conversation, if necessary, in a situation in which a user and a system have a conversation based on text or a voice. The multi-modal chatting apparatus includes a text response generation unit configured to generate a text system response that needs to be now spoken based on conversation context between a system and a user, a picture expression generation unit configured to generate picture expression text that expresses contents to be expressed by a picture based on the generated text system response, and a picture generation unit configured to generate a picture based on the generated picture expression text.

Abstract: The present disclosure provides a thin film transistor comprising a gate electrode, an active layer, a source electrode, and a drain electrode, wherein the active layer includes a first channel part overlapping the source electrode, a second channel part overlapping the drain electrode, and a connection part connecting the first channel part and the second channel part, and the connection part is a conductorized region. Additionally, a manufacturing method of the thin film transistor and a display apparatus including the thin film transistor mentioned above are disclosed.

Abstract: Disclosed are a method and apparatus for generating personalized information using a generative language model and presenting generated results that suit a user based on the generated personalized information. An apparatus for personalization of a generative language model includes: a personalized information memory that stores personalized information of a user; and a personalized query generation unit that generates a personalized query prompt including personalized information from a user query input by the user using the personalized information stored in the personalized information memory. In an embodiment, the apparatus may further include a latest result memory that stores a question-response pair for a predetermined period, and a personalized information extraction unit that extracts information utilized as the personalized information from the question-response pair stored in the latest result memory and stores the extracted information in the personalized information memory.

Abstract: A thin film transistor comprises: an active layer; and a gate electrode overlapping the active layer, wherein the active layer comprises: a channel portion; a first conductive portion disposed on one side of the channel portion; and a second conductive portion disposed on the other side of the channel portion, wherein the first conductive portion comprises: a first hydrogen conducting portion; and a first connection portion disposed between the first hydrogen conducting portion and the channel portion, and wherein the second conductive portion comprises: a second hydrogen conducting portion; and a second connection portion disposed between the second hydrogen conducting portion and the channel portion, wherein a surface resistance of the first hydrogen conducting portion is greater than a surface resistance of the first connection portion, and a surface resistance of the second hydrogen conducting portion is greater than a surface resistance of the second connection portion.

Abstract: Provided is a method of generating a language model using crossmodal information. The method includes: receiving language-based first modality information and non-language-based second modality information; converting the first modality information into a first byte sequence; converting the second modality information into a second byte sequence; converting the first and second byte sequences into a first embedding vector and a second embedding vector by applying an embedding technique for each modality; generating semantic association information between first and second modality information by inputting the first and second embedding vectors to a crossmodal transformer; and learning the language model by setting the generated semantic association information as training data.

Abstract: A thin film transistor, a thin film transistor substrate, a method of manufacturing a thin film transistor and a display apparatus including the thin film transistor are provided. The thin film transistor includes a base substrate, an active material layer on the base substrate, and a gate electrode spaced apart from the active material layer and overlapping at least a portion of the active material layer. The active material layer includes a channel portion overlapping the gate electrode, a source connection portion contacting one side of the channel portion, a drain connection portion contacting the other side of the channel portion and an insulating portion contacting at least one of the source connection portion and the drain connection portion. Further, the channel portion, the source connection portion, the drain connection portion, and the insulating portion are disposed on a same layer.

Abstract: A method for problem inference based on multi-modal generative artificial intelligence includes receiving question information including an image and text, generating formal languages by parsing the image and text of the question information, respectively, based on a pre-constructed problem solving template, generating text-based intermediate inference information for the question information by inputting the generated formal language to a formal language inference unit, generating image-based inference information by inputting the text-based intermediate inference information, the text included in the question information (hereinafter referred to as “text question information”), and the image included in the question information (hereinafter referred to as “image question information”) to a multi-modal image generation model, and generating text-based inference information by inputting the text-based intermediate inference information, the image-based inference information, and the text question information

Abstract: The present disclosure relates to a question answering system and method capable of inferring multiple correct answers. The question answering system capable of inferring multiple correct answers according to the present disclosure includes an input interface device configured to receive a query, a memory for storing a program that analyzes the query and searches for a paragraph with a high probability of including a correct answer through a document search, and a processor for executing the program, wherein the processor extracts a correct answer using a result of the searching for a paragraph with a high probability of including a correct answer, determines whether the extracted correct answer corresponds to multiple correct answers, and provides a correct answer extraction result.

Abstract: Provided is a method of generating a language model using crossmodal information. The method includes: receiving language-based first modality information and non-language-based second modality information; converting the first modality information into a first byte sequence; converting the second modality information into a second byte sequence; converting the first and second byte sequences into a first embedding vector and a second embedding vector by applying an embedding technique for each modality; generating semantic association information between first and second modality information by inputting the first and second embedding vectors to a crossmodal transformer; and learning the language model by setting the generated semantic association information as training data.

Abstract: A holographic characterization and playback apparatus is provided, which includes a light source, an optical path-forming optical system for separating the light emitted from the light source into a probe light and a reference light of different polarizations, and combining optical paths of the probe light and the reference light.

Abstract: A holographic characterization and playback apparatus is provided, which includes a light source, an optical path-forming optical system for separating the light emitted from the light source into a probe light and a reference light of different polarizations, and combining optical paths of the probe light and the reference light.