Argumentation theory

Argumentation theory is the interdisciplinary study of how conclusions can be supported or undermined by premises through logical reasoning. With historical origins in logic, dialectic, and rhetoric, argumentation theory includes the arts and sciences of civil debate, dialogue, conversation, and persuasion. It studies rules of inference, logic, and procedural rules in both artificial and real-world settings. Argumentation includes various forms of dialogue such as deliberation and negotiation which are concerned with collaborative decision-making procedures. It also encompasses eristic dialogue, the branch of social debate in which victory over an opponent is the primary goal, and didactic dialogue used for teaching. This discipline also studies the means by which people can express and rationally resolve or at least manage their disagreements. Argumentation is a daily occurrence, such as in public debate, science, and law. For example in law, in courts by the judge, the parties and the prosecutor, in presenting and testing the validity of evidences. Also, argumentation scholars study the post hoc rationalizations by which organizational actors try to justify decisions they have made irrationally. Argumentation is one of four rhetorical modes (also known as modes of discourse), along with exposition, description, and narration. == Key components of argumentation == Some key components of argumentation are: Understanding and identifying arguments, either explicit or implied, and the goals of the participants in the different types of dialogue. Identifying the premises from which conclusions are derived. Establishing the "burden of proof" – determining who made the initial claim and is thus responsible for providing evidence why their position merits acceptance. For the one carrying the "burden of proof", the advocate, to marshal evidence for their position in order to convince or force the opponent's acceptance. The method by which this is accomplished is producing valid, sound, and cogent arguments, devoid of weaknesses, and not easily attacked. In a debate, fulfillment of the burden of proof creates a burden of rejoinder. One must try to identify faulty reasoning in the opponent's argument, to attack the reasons/premises of the argument, to provide counterexamples if possible, to identify any fallacies, and to show why a valid conclusion cannot be derived from the reasons provided for their argument. For example, consider the following exchange, illustrating the No true Scotsman fallacy: Argument: "No Scotsman puts sugar on his porridge." Reply: "But my friend Angus, who is a Scotsman, likes sugar with his porridge." Rebuttal: "Well perhaps, but no true Scotsman puts sugar on his porridge." In this dialogue, the proposer first offers a premise, the premise is challenged by the interlocutor, and so the proposer offers a modification of the premise, which is designed only to evade the challenge provided. == Internal structure of arguments == Typically an argument has an internal structure, comprising the following: a set of assumptions or premises, a method of reasoning or deduction, and a conclusion or point. An argument has one or more premises and one conclusion. Often classical logic is used as the method of reasoning so that the conclusion follows logically from the assumptions or support. One challenge is that if the set of assumptions is inconsistent then anything can follow logically from inconsistency. Therefore, it is common to insist that the set of assumptions be consistent. It is also good practice to require the set of assumptions to be the minimal set, with respect to set inclusion, necessary to infer the consequent. Such arguments are called MINCON arguments, short for minimal consistent. Such argumentation has been applied to the fields of law and medicine. A non-classical approach to argumentation investigates abstract arguments, where 'argument' is considered a primitive term, so no internal structure of arguments is taken into account. == Types of dialogue == In its most common form, argumentation involves an individual and an interlocutor or opponent engaged in dialogue, each contending differing positions and trying to persuade each other, but there are various types of dialogue: Persuasion dialogue aims to resolve conflicting points of view of different positions. Negotiation aims to resolve conflicts of interests by cooperation and dealmaking. Inquiry aims to resolve general ignorance by the growth of knowledge. Deliberation aims to resolve a need to take action by reaching a decision. Information seeking aims to reduce one party's ignorance by requesting information from another party that is in a position to know something. Eristic aims to resolve a situation of antagonism through verbal fighting. == Argumentation and the grounds of knowledge == Argumentation theory had its origins in foundationalism, a theory of knowledge (epistemology) in the field of philosophy. It sought to find the grounds for claims in the forms (logic) and materials (factual laws) of a universal system of knowledge. The dialectical method was made famous by Plato and his use of Socrates critically questioning various characters and historical figures. But argument scholars gradually rejected Aristotle's systematic philosophy and the idealism in Plato and Kant. They questioned and ultimately discarded the idea that argument premises take their soundness from formal philosophical systems. The field thus broadened. One of the original contributors to this trend was the philosopher Chaïm Perelman, who together with Lucie Olbrechts-Tyteca introduced the French term la nouvelle rhetorique in 1958 to describe an approach to argument which is not reduced to application of formal rules of inference. Perelman's view of argumentation is much closer to a juridical one, in which rules for presenting evidence and rebuttals play an important role. Karl R. Wallace's seminal essay, "The Substance of Rhetoric: Good Reasons" in the Quarterly Journal of Speech (1963) 44, led many scholars to study "marketplace argumentation" – the ordinary arguments of ordinary people. The seminal essay on marketplace argumentation is Ray Lynn Anderson's and C. David Mortensen's "Logic and Marketplace Argumentation" Quarterly Journal of Speech 53 (1967): 143–150. This line of thinking led to a natural alliance with late developments in the sociology of knowledge. Some scholars drew connections with recent developments in philosophy, namely the pragmatism of John Dewey and Richard Rorty. Rorty has called this shift in emphasis "the linguistic turn". In this new hybrid approach argumentation is used with or without empirical evidence to establish convincing conclusions about issues which are moral, scientific, epistemic, or of a nature in which science alone cannot answer. Out of pragmatism and many intellectual developments in the humanities and social sciences, "non-philosophical" argumentation theories grew which located the formal and material grounds of arguments in particular intellectual fields. These theories include informal logic, social epistemology, ethnomethodology, speech acts, the sociology of knowledge, the sociology of science, and social psychology. These new theories are not non-logical or anti-logical. They find logical coherence in most communities of discourse. These theories are thus often labeled "sociological" in that they focus on the social grounds of knowledge. == Kinds of argumentation == === Conversational argumentation === The study of naturally occurring conversation arose from the field of sociolinguistics. It is usually called conversation analysis (CA). Inspired by ethnomethodology, it was developed in the late 1960s and early 1970s principally by the sociologist Harvey Sacks and, among others, his close associates Emanuel Schegloff and Gail Jefferson. Sacks died early in his career, but his work was championed by others in his field, and CA has now become an established force in sociology, anthropology, linguistics, speech-communication and psychology. It is particularly influential in interactional sociolinguistics, discourse analysis and discursive psychology, as well as being a coherent discipline in its own right. Recently CA techniques of sequential analysis have been employed by phoneticians to explore the fine phonetic details of speech. Empirical studies and theoretical formulations by Sally Jackson and Scott Jacobs, and several generations of their students, have described argumentation as a form of managing conversational disagreement within communication contexts and systems that naturally prefer agreement. === Mathematical argumentation === The basis of mathematical truth has been the subject of long debate. Frege in particular sought to demonstrate (see Gottlob Frege, The Foundations of Arithmetic, 1884, and Begriffsschrift, 1879) that arithmetical truths can be derived from purely logical axioms and therefore are, in th

Mean shift

Mean shift is a non-parametric feature-space mathematical analysis technique for locating the maxima of a density function, a so-called mode-seeking algorithm. Application domains include cluster analysis in computer vision and image processing. == History == The mean shift procedure is usually credited to work by Fukunaga and Hostetler in 1975. It is, however, reminiscent of earlier work by Schnell in 1964. == Overview == Mean shift is a procedure for locating the maxima—the modes—of a density function given discrete data sampled from that function. This is an iterative method, and we start with an initial estimate x {\displaystyle x} . Let a kernel function K ( x i − x ) {\displaystyle K(x_{i}-x)} be given. This function determines the weight of nearby points for re-estimation of the mean. Typically a Gaussian kernel on the distance to the current estimate is used, K ( x i − x ) = e − c | | x i − x | | 2 {\displaystyle K(x_{i}-x)=e^{-c||x_{i}-x||^{2}}} . The weighted mean of the density in the window determined by K {\displaystyle K} is m ( x ) = ∑ x i ∈ N ( x ) K ( x i − x ) x i ∑ x i ∈ N ( x ) K ( x i − x ) {\displaystyle m(x)={\frac {\sum _{x_{i}\in N(x)}K(x_{i}-x)x_{i}}{\sum _{x_{i}\in N(x)}K(x_{i}-x)}}} where N ( x ) {\displaystyle N(x)} is the neighborhood of x {\displaystyle x} , a set of points for which K ( x i − x ) ≠ 0 {\displaystyle K(x_{i}-x)\neq 0} . The difference m ( x ) − x {\displaystyle m(x)-x} is called mean shift in Fukunaga and Hostetler. The mean-shift algorithm now sets x ← m ( x ) {\displaystyle x\leftarrow m(x)} , and repeats the estimation until m ( x ) {\displaystyle m(x)} converges. Although the mean shift algorithm has been widely used in many applications, a rigid proof for the convergence of the algorithm using a general kernel in a high dimensional space is still not known. Aliyari Ghassabeh showed the convergence of the mean shift algorithm in one dimension with a differentiable, convex, and strictly decreasing profile function. However, the one-dimensional case has limited real world applications. Also, the convergence of the algorithm in higher dimensions with a finite number of the stationary (or isolated) points has been proved. However, sufficient conditions for a general kernel function to have finite stationary (or isolated) points have not been provided. Gaussian Mean-Shift is an Expectation–maximization algorithm. == Details == Let data be a finite set S {\displaystyle S} embedded in the n {\displaystyle n} -dimensional Euclidean space, X {\displaystyle X} . Let K {\displaystyle K} be a flat kernel that is the characteristic function of the λ {\displaystyle \lambda } -ball in X {\displaystyle X} , In each iteration of the algorithm, s ← m ( s ) {\displaystyle s\leftarrow m(s)} is performed for all s ∈ S {\displaystyle s\in S} simultaneously. The first question, then, is how to estimate the density function given a sparse set of samples. One of the simplest approaches is to just smooth the data, e.g., by convolving it with a fixed kernel of width h {\displaystyle h} , where x i {\displaystyle x_{i}} are the input samples and k ( r ) {\displaystyle k(r)} is the kernel function (or Parzen window). h {\displaystyle h} is the only parameter in the algorithm and is called the bandwidth. This approach is known as kernel density estimation or the Parzen window technique. Once we have computed f ( x ) {\displaystyle f(x)} from the equation above, we can find its local maxima using gradient ascent or some other optimization technique. The problem with this "brute force" approach is that, for higher dimensions, it becomes computationally prohibitive to evaluate f ( x ) {\displaystyle f(x)} over the complete search space. Instead, mean shift uses a variant of what is known in the optimization literature as multiple restart gradient descent. Starting at some guess for a local maximum, y k {\displaystyle y_{k}} , which can be a random input data point x 1 {\displaystyle x_{1}} , mean shift computes the gradient of the density estimate f ( x ) {\displaystyle f(x)} at y k {\displaystyle y_{k}} and takes an uphill step in that direction. == Types of kernels == Kernel definition: Let X {\displaystyle X} be the n {\displaystyle n} -dimensional Euclidean space, R n {\displaystyle \mathbb {R} ^{n}} . The norm of x {\displaystyle x} is a non-negative number, ‖ x ‖ 2 = x ⊤ x ≥ 0 {\displaystyle \|x\|^{2}=x^{\top }x\geq 0} . A function K : X → R {\displaystyle K:X\rightarrow \mathbb {R} } is said to be a kernel if there exists a profile, k : [ 0 , ∞ ] → R {\displaystyle k:[0,\infty ]\rightarrow \mathbb {R} } , such that K ( x ) = k ( ‖ x ‖ 2 ) {\displaystyle K(x)=k(\|x\|^{2})} and k is non-negative. k is non-increasing: k ( a ) ≥ k ( b ) {\displaystyle k(a)\geq k(b)} if a < b {\displaystyle a

Xiaomi MiMo

Xiaomi MiMo is a family of large language models (LLMs) developed by Xiaomi. It was initially released in April 2025 with the MiMo-7B model. Currently, MiMo is available for developers through API service. It is used as the key AI model in Xiaomi's "Human x Car x Home" ecosystem. == Development == Xiaomi developed MiMo as a reasoning-focused language model. Its development team was led by Luo Fuli, who had previously worked at DeepSeek before joining Xiaomi in late 2025. The model was trained using multi-token prediction and reinforcement learning, with a particular emphasis on mathematical reasoning and code generation tasks. In March 2026, Xiaomi CEO Lei Jun announced that the company planned to invest at least US$8.7 billion in artificial intelligence over the following three years. == Models == === List of models === === MiMo-7B === MiMo-7B is the first model of this LLM. The base model, MiMo-7B-Base, was pre-trained on approximately 25 trillion tokens using web pages, academic papers, books, and synthetic reasoning data. MiMo-7B-RL underwent supervised fine-tuning and reinforcement learning on 130,000 mathematics and code problems. MiMo-7B-RL-0530 was released in May 2025. It scaled the fine-tuning dataset from 500,000 to 6 million instances and extended the RL window from 32,000 to 48,000 tokens and improved AIME 2024 scores from 68.2 to 80.1. MiMo-VL-7B was a vision-language model combining a Vision Transformer encoder with the MiMo-7B backbone. It was trained in four stages consuming 2.4 trillion tokens. Its reinforcement learning variant used Mixed On-Policy Reinforcement Learning (MORL) which integrated reward signals across perception, grounding, and reasoning. Xiaomi also released MiMo-Audio-7B, an audio-language model for voice conversion, style transfer, and speech editing. === MiMo-V2-Flash === MiMo-V2-Flash was launched in December 2025. It is a open-sourced Mixture-of-experts model with 309 billion total parameters and 15 billion active parameters. It was trained on 27 trillion tokens using FP8 mixed precision. It used hybrid attention interleaving Sliding Window and Global Attention at a 5:1 ratio. === MiMo-V2-Pro === Xiaomi publicly introduced MiMo-V2-Pro on 18 March 2026. It has over 1 trillion total parameters, 42 billion active, and a 1-million-token context window. Before the official release, the model had appeared anonymously on OpenRouter under the codename "Hunter Alpha," where it drew substantial usage and topped daily charts for several days, according to Xiaomi and Reuters. During its listing on OpenRouter, the model reportedly processed over one trillion tokens in total usage. Xiaomi later said Hunter Alpha was an early internal test build of MiMo-V2-Pro, and Reuters reported that the model had been mistaken by some users for a possible DeepSeek system before Xiaomi confirmed its origin. The model was released as a proprietary API product, and Luo Fuli stated that Xiaomi intended to open-source a variant at an unspecified future date. Xiaomi has partnered with several API web platforms like OpenClaw to launch the model. All these websites initially offered a free trial of this model for a week, but due to the overwhelming response, Xiaomi later extended the free trial period of the model until 2 April 2026. === MiMo-V2-Omni === Alongside MiMo-V2-Pro, Xiaomi launched MiMo-V2-Omni on 18 March 2026. It handles image, video, audio, and text inputs. Before the official release, it was codenamed "Healer Alpha" in OpenRouter. === MiMo-V2-TTS === On the same date as the release of MiMo-V2-Pro and MiMo-V2-Omni, a Text-to-Speech model named MiMo-V2-TTS was released also. It is a speech synthesis model. It was trained on audio data, which makes it capable of emotional transitions, mid-sentence tone shifts, singing, and synthesis of regional dialects like Sichuan, Cantonese, Henan, and Taiwanese. == Licensing == Xiaomi has used different licensing approaches for different models in the MiMo family. The MiMo-7B series and MiMo-V2-Flash were released as open-weight models. MiMo-V2-Flash was published under the MIT license with model weights and inference code available on Hugging Face. MiMo-V2-Pro and MiMo-V2-Omni were released as proprietary models. It was accessible through Xiaomi's API platform and third-party API providers. Luo Fuli stated that Xiaomi intended to open-source a variant of MiMo-V2-Pro. Although, she did not specify any timeline. MiMo-V2-TTS was released as a proprietary model with no publicly available weights.

Visual servoing

Visual servoing, also known as vision-based robot control and abbreviated VS, is a technique which uses feedback information extracted from a vision sensor (visual feedback) to control the motion of a robot. One of the earliest papers that talks about visual servoing was from the SRI International Labs in 1979. == Visual servoing taxonomy == There are two fundamental configurations of the robot end-effector (hand) and the camera: Eye-in-hand, or end-point open-loop control, where the camera is attached to the moving hand and observing the relative position of the target. Eye-to-hand, or end-point closed-loop control, where the camera is fixed in the world and observing the target and the motion of the hand. Visual Servoing control techniques are broadly classified into the following types: Image-based (IBVS) Position/pose-based (PBVS) Hybrid approach IBVS was proposed by Weiss and Sanderson. The control law is based on the error between current and desired features on the image plane, and does not involve any estimate of the pose of the target. The features may be the coordinates of visual features, lines or moments of regions. IBVS has difficulties with motions very large rotations, which has come to be called camera retreat. PBVS is a model-based technique (with a single camera). This is because the pose of the object of interest is estimated with respect to the camera and then a command is issued to the robot controller, which in turn controls the robot. In this case the image features are extracted as well, but are additionally used to estimate 3D information (pose of the object in Cartesian space), hence it is servoing in 3D. Hybrid approaches use some combination of the 2D and 3D servoing. There have been a few different approaches to hybrid servoing 2-1/2-D Servoing Motion partition-based Partitioned DOF Based == Survey == The following description of the prior work is divided into 3 parts Survey of existing visual servoing methods. Various features used and their impacts on visual servoing. Error and stability analysis of visual servoing schemes. === Survey of existing visual servoing methods === Visual servo systems, also called servoing, have been around since the early 1980s , although the term visual servo itself was only coined in 1987. Visual Servoing is, in essence, a method for robot control where the sensor used is a camera (visual sensor). Servoing consists primarily of two techniques, one involves using information from the image to directly control the degrees of freedom (DOF) of the robot, thus referred to as Image Based Visual Servoing (IBVS). While the other involves the geometric interpretation of the information extracted from the camera, such as estimating the pose of the target and parameters of the camera (assuming some basic model of the target is known). Other servoing classifications exist based on the variations in each component of a servoing system , e.g. the location of the camera, the two kinds are eye-in-hand and hand–eye configurations. Based on the control loop, the two kinds are end-point-open-loop and end-point-closed-loop. Based on whether the control is applied to the joints (or DOF) directly or as a position command to a robot controller the two types are direct servoing and dynamic look-and-move. Being one of the earliest works the authors proposed a hierarchical visual servo scheme applied to image-based servoing. The technique relies on the assumption that a good set of features can be extracted from the object of interest (e.g. edges, corners and centroids) and used as a partial model along with global models of the scene and robot. The control strategy is applied to a simulation of a two and three DOF robot arm. Feddema et al. introduced the idea of generating task trajectory with respect to the feature velocity. This is to ensure that the sensors are not rendered ineffective (stopping the feedback) for any the robot motions. The authors assume that the objects are known a priori (e.g. CAD model) and all the features can be extracted from the object. The work by Espiau et al. discusses some of the basic questions in visual servoing. The discussions concentrate on modeling of the interaction matrix, camera, visual features (points, lines, etc..). In an adaptive servoing system was proposed with a look-and-move servoing architecture. The method used optical flow along with SSD to provide a confidence metric and a stochastic controller with Kalman filtering for the control scheme. The system assumes (in the examples) that the plane of the camera and the plane of the features are parallel., discusses an approach of velocity control using the Jacobian relationship s˙ = Jv˙ . In addition the author uses Kalman filtering, assuming that the extracted position of the target have inherent errors (sensor errors). A model of the target velocity is developed and used as a feed-forward input in the control loop. Also, mentions the importance of looking into kinematic discrepancy, dynamic effects, repeatability, settling time oscillations and lag in response. Corke poses a set of very critical questions on visual servoing and tries to elaborate on their implications. The paper primarily focuses the dynamics of visual servoing. The author tries to address problems like lag and stability, while also talking about feed-forward paths in the control loop. The paper also, tries to seek justification for trajectory generation, methodology of axis control and development of performance metrics. Chaumette in provides good insight into the two major problems with IBVS. One, servoing to a local minima and second, reaching a Jacobian singularity. The author show that image points alone do not make good features due to the occurrence of singularities. The paper continues, by discussing the possible additional checks to prevent singularities namely, condition numbers of J_s and Jˆ+_s, to check the null space of ˆ J_s and J^T_s . One main point that the author highlights is the relation between local minima and unrealizable image feature motions. Over the years many hybrid techniques have been developed. These involve computing partial/complete pose from Epipolar Geometry using multiple views or multiple cameras. The values are obtained by direct estimation or through a learning or a statistical scheme. While others have used a switching approach that changes between image-based and position-based on a Lyapnov function. The early hybrid techniques that used a combination of image-based and pose-based (2D and 3D information) approaches for servoing required either a full or partial model of the object in order to extract the pose information and used a variety of techniques to extract the motion information from the image. used an affine motion model from the image motion in addition to a rough polyhedral CAD model to extract the object pose with respect to the camera to be able to servo onto the object (on the lines of PBVS). 2-1/2-D visual servoing developed by Malis et al. is a well known technique that breaks down the information required for servoing into an organized fashion which decouples rotations and translations. The papers assume that the desired pose is known a priori. The rotational information is obtained from partial pose estimation, a homography, (essentially 3D information) giving an axis of rotation and the angle (by computing the eigenvalues and eigenvectors of the homography). The translational information is obtained from the image directly by tracking a set of feature points. The only conditions being that the feature points being tracked never leave the field of view and that a depth estimate be predetermined by some off-line technique. 2-1/2-D servoing has been shown to be more stable than the techniques that preceded it. Another interesting observation with this formulation is that the authors claim that the visual Jacobian will have no singularities during the motions. The hybrid technique developed by Corke and Hutchinson, popularly called portioned approach partitions the visual (or image) Jacobian into motions (both rotations and translations) relating X and Y axes and motions related to the Z axis. outlines the technique, to break out columns of the visual Jacobian that correspond to the Z axis translation and rotation (namely, the third and sixth columns). The partitioned approach is shown to handle the Chaumette Conundrum discussed in. This technique requires a good depth estimate in order to function properly. outlines a hybrid approach where the servoing task is split into two, namely main and secondary. The main task is keep the features of interest within the field of view. While the secondary task is to mark a fixation point and use it as a reference to bring the camera to the desired pose. The technique does need a depth estimate from an off-line procedure. The paper discusses two examples for which depth estimates are obtained from robot odometry and by assuming that all

Automatic summarization

Automatic summarization is the process of shortening a set of data computationally, to create a subset (a summary) that represents the most important or relevant information within the original content. Artificial intelligence (AI) algorithms are commonly developed and employed to achieve this, specialized for different types of data. Text summarization is usually implemented by natural language processing methods, designed to locate the most informative sentences in a given document. On the other hand, visual content can be summarized using computer vision algorithms. Image summarization is the subject of ongoing research; existing approaches typically attempt to display the most representative images from a given image collection, or generate a video that only includes the most important content from the entire collection. Video summarization algorithms identify and extract from the original video content the most important frames (key-frames), and/or the most important video segments (key-shots), normally in a temporally ordered fashion. Video summaries simply retain a carefully selected subset of the original video frames and, therefore, are not identical to the output of video synopsis algorithms, where new video frames are being synthesized based on the original video content. == Commercial products == In 2022 Google Docs released an automatic summarization feature. == Approaches == There are two general approaches to automatic summarization: extraction and abstraction. === Extraction-based summarization === Here, content is extracted from the original data, but the extracted content is not modified in any way. Examples of extracted content include key-phrases that can be used to "tag" or index a text document, or key sentences (including headings) that collectively comprise an abstract, and representative images or video segments, as stated above. For text, extraction is analogous to the process of skimming, where the summary (if available), headings and subheadings, figures, the first and last paragraphs of a section, and optionally the first and last sentences in a paragraph are read before one chooses to read the entire document in detail. Other examples of extraction that include key sequences of text in terms of clinical relevance (including patient/problem, intervention, and outcome). === Abstractive-based summarization === Abstractive summarization methods generate new text that did not exist in the original text. This has been applied mainly for text. Abstractive methods build an internal semantic representation of the original content (often called a language model), and then use this representation to create a summary that is closer to what a human might express. Abstraction may transform the extracted content by paraphrasing sections of the source document, to condense a text more strongly than extraction. Such transformation, however, is computationally much more challenging than extraction, involving both natural language processing and often a deep understanding of the domain of the original text in cases where the original document relates to a special field of knowledge. "Paraphrasing" is even more difficult to apply to images and videos, which is why most summarization systems are extractive. === Aided summarization === Approaches aimed at higher summarization quality rely on combined software and human effort. In Machine Aided Human Summarization, extractive techniques highlight candidate passages for inclusion (to which the human adds or removes text). In Human Aided Machine Summarization, a human post-processes software output, in the same way that one edits the output of automatic translation by Google Translate. == Applications and systems for summarization == There are broadly two types of extractive summarization tasks depending on what the summarization program focuses on. The first is generic summarization, which focuses on obtaining a generic summary or abstract of the collection (whether documents, or sets of images, or videos, news stories etc.). The second is query relevant summarization, sometimes called query-based summarization, which summarizes objects specific to a query. Summarization systems are able to create both query relevant text summaries and generic machine-generated summaries depending on what the user needs. An example of a summarization problem is document summarization, which attempts to automatically produce an abstract from a given document. Sometimes one might be interested in generating a summary from a single source document, while others can use multiple source documents (for example, a cluster of articles on the same topic). This problem is called multi-document summarization. A related application is summarizing news articles. Imagine a system, which automatically pulls together news articles on a given topic (from the web), and concisely represents the latest news as a summary. Image collection summarization is another application example of automatic summarization. It consists in selecting a representative set of images from a larger set of images. A summary in this context is useful to show the most representative images of results in an image collection exploration system. Video summarization is a related domain, where the system automatically creates a trailer of a long video. This also has applications in consumer or personal videos, where one might want to skip the boring or repetitive actions. Similarly, in surveillance videos, one would want to extract important and suspicious activity, while ignoring all the boring and redundant frames captured. At a very high level, summarization algorithms try to find subsets of objects (like set of sentences, or a set of images), which cover information of the entire set. This is also called the core-set. These algorithms model notions like diversity, coverage, information and representativeness of the summary. Query based summarization techniques, additionally model for relevance of the summary with the query. Some techniques and algorithms which naturally model summarization problems are TextRank and PageRank, Submodular set function, Determinantal point process, maximal marginal relevance (MMR) etc. === Keyphrase extraction === The task is the following. You are given a piece of text, such as a journal article, and you must produce a list of keywords or key[phrase]s that capture the primary topics discussed in the text. In the case of research articles, many authors provide manually assigned keywords, but most text lacks pre-existing keyphrases. For example, news articles rarely have keyphrases attached, but it would be useful to be able to automatically do so for a number of applications discussed below. Consider the example text from a news article: "The Army Corps of Engineers, rushing to meet President Bush's promise to protect New Orleans by the start of the 2006 hurricane season, installed defective flood-control pumps last year despite warnings from its own expert that the equipment would fail during a storm, according to documents obtained by The Associated Press". A keyphrase extractor might select "Army Corps of Engineers", "President Bush", "New Orleans", and "defective flood-control pumps" as keyphrases. These are pulled directly from the text. In contrast, an abstractive keyphrase system would somehow internalize the content and generate keyphrases that do not appear in the text, but more closely resemble what a human might produce, such as "political negligence" or "inadequate protection from floods". Abstraction requires a deep understanding of the text, which makes it difficult for a computer system. Keyphrases have many applications. They can enable document browsing by providing a short summary, improve information retrieval (if documents have keyphrases assigned, a user could search by keyphrase to produce more reliable hits than a full-text search), and be employed in generating index entries for a large text corpus. Depending on the different literature and the definition of key terms, words or phrases, keyword extraction is a highly related theme. ==== Supervised learning approaches ==== Beginning with the work of Turney, many researchers have approached keyphrase extraction as a supervised machine learning problem. Given a document, we construct an example for each unigram, bigram, and trigram found in the text (though other text units are also possible, as discussed below). We then compute various features describing each example (e.g., does the phrase begin with an upper-case letter?). We assume there are known keyphrases available for a set of training documents. Using the known keyphrases, we can assign positive or negative labels to the examples. Then we learn a classifier that can discriminate between positive and negative examples as a function of the features. Some classifiers make a binary classification for a test example, while others assign a probability of being a keyphrase. For ins

Color moments

Color moments are measures that characterise color distribution in an image in the same way that central moments uniquely describe a probability distribution. Color moments are mainly used for color indexing purposes as features in image retrieval applications in order to compare how similar two images are based on color. Usually one image is compared to a database of digital images with pre-computed features in order to find and retrieve a similar Image. Each comparison between images results in a similarity score, and the lower this score is the more identical the two images are supposed to be. == Overview == Color moments are scaling and rotation invariant. It is usually the case that only the first three color moments are used as features in image retrieval applications as most of the color distribution information is contained in the low-order moments. Since color moments encode both shape and color information they are a good feature to use under changing lighting conditions, but they cannot handle occlusion very successfully. Color moments can be computed for any color model. Three color moments are computed per channel (e.g. 9 moments if the color model is RGB and 12 moments if the color model is CMYK). Computing color moments is done in the same way as computing moments of a probability distribution. === Mean === The first color moment can be interpreted as the average color in the image, and it can be calculated by using the following formula E i = ∑ j = 1 N 1 N p i j {\displaystyle E_{i}=\textstyle \sum _{j=1}^{N}{\frac {1}{N}}p_{ij}} where N is the number of pixels in the image and p i j {\displaystyle p_{ij}} is the value of the j-th pixel of the image at the i-th color channel. === Standard Deviation === The second color moment is the standard deviation, which is obtained by taking the square root of the variance of the color distribution. σ i = ( 1 N ∑ j = 1 N ( p i j − E i ) 2 ) {\displaystyle \sigma _{i}={\sqrt {({\frac {1}{N}}\textstyle \sum _{j=1}^{N}(p_{ij}-E_{i})^{2})}}} where E i {\displaystyle E_{i}} is the mean value, or first color moment, for the i-th color channel of the image. === Skewness === The third color moment is the skewness. It measures how asymmetric the color distribution is, and thus it gives information about the shape of the color distribution. Skewness can be computed with the following formula: s i = ( 1 N ∑ j = 1 N ( p i j − E i ) 3 ) 3 σ i {\displaystyle s_{i}={\frac {\sqrt[{3}]{\left({\frac {1}{N}}\textstyle \sum _{j=1}^{N}(p_{ij}-E_{i})^{3}\right)}}{\sigma _{i}}}} === Kurtosis === Kurtosis is the fourth color moment, and, similarly to skewness, it provides information about the shape of the color distribution. More specifically, kurtosis is a measure of how extreme the tails are in comparison to the normal distribution. === Higher-order color moments === Higher-order color moments are usually not part of the color moments feature set in image retrieval tasks as they require more data in order to obtain a good estimate of their value, and also the lower-order moments generally provide enough information. == Applications == Color moments have significant applications in image retrieval. They can be used in order to compare how similar two images are. This is a relatively new approach to color indexing. The greatest advantage of using color moments comes from the fact that there is no need to store the complete color distribution. This greatly speeds up image retrieval since there are less features to compare. In addition, the first three color moments have the same units, which allows for comparison between them. === Color indexing === Color indexing is the main application of color moments. Images can be indexed, and the index will contain the computed color moments. Then, if someone has a particular image and wants to find similar images in the database, the color moments of the image of interest will also be computed. After that the following function will be used in order to compute a similarity score between the image of interest and all the images in the database: d m o m ( H , I ) = ∑ i = 1 r w i 1 | E i 1 − E i 2 | + w i 2 | σ i 1 − σ i 2 | + w i 3 | s i 1 − s i 2 | {\displaystyle d_{mom}(H,I)=\textstyle \sum _{i=1}^{r}w_{i1}|E_{i}^{1}-E_{i}^{2}|+w_{i2}|\sigma _{i}^{1}-\sigma _{i}^{2}|+w_{i3}|s_{i}^{1}-s_{i}^{2}|} where: H and I are the color distributions of the two images that are being compared i is the channel index and r is the total number of channels E i 1 {\displaystyle E_{i}^{1}} and E i 2 {\displaystyle E_{i}^{2}} are the first order moments computed for the image distributions. σ i 1 {\displaystyle \sigma _{i}^{1}} and σ i 2 {\displaystyle \sigma _{i}^{2}} are the second order moments computed for the image distributions. s_i^1 and s_i^2 are the third order moments computed for the image distributions. w i 1 {\displaystyle w_{i1}} , w i 2 {\displaystyle w_{i2}} , and w i 3 {\displaystyle w_{i3}} are weights, specified by the user, for each of the three color moments used. Finally, the images in the database will be ranked according to the computed similarity score with the image of interest, and the database images with the lowest d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} value should be retrieved. "A retrieval based on d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} may produce false positives because the index contains no information about the correlation between the color channels". == Example == A simple and concise example of the use of color moments for image retrieval tasks is illustrated in. Consider having several test images in a database and a "New Image". The goal is to retrieve images from the database that are similar to the "New Image". The first three color moments are used as features. There are several steps in this computation. Image preprocessing (Optional) - The image preprocessing step of the computation process is optional. For example, in this step all images could be modified to be the same size (in terms of pixels). However, since color moments are invariant to scaling, it is not necessary to make all images the same width and height. Computing the features - Use the color moments formulae in order to compute the first three moments for each of the color channels in the image. For example, if the HSV color space is used, this means that for each of the images, 9 features in total will be computed (the first three order moments for the Hue, Saturation, and Value channels). Calculating the similarity score - After computing the color moments the weights for each of the moments in the d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} function should be determined by the user. The weights have to be adjusted each time in accordance with the application or condition and quality of the images. Following that the d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} function is used to calculate a similarity score for the "New Image" and each of the images in the database. Ranking and image retrieval - From the previous step the d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} values were obtained. Now a comparison of these values can be made in order to decide which of the images in the database are more similar to the "New Image", and thus rank the database images accordingly. The smaller the d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} value is the more similar the two color distributions are supposed to be. Finally, some of the top ranked images (the ones with the smallest d m o m ( H , I ) {\displaystyle d_{mom}(H,I)} value) from the database are retrieved.

Character.ai

Character.ai (also known as c.ai, char.ai or Character AI) is a generative AI chatbot service where users can engage in conversations with customizable characters. It was designed by the developers of Google LaMDA, Noam Shazeer and Daniel de Freitas. Users can create "characters", craft their "personalities", set specific parameters, and then publish them to the community for others to chat with. Many characters are based on fictional media sources or celebrities, while others are original, some being made with certain goals in mind, such as assisting with creative writing, or playing a text-based adventure game. The beta version was made available to the public on September 16, 2022, and retired in September 2024, when it was replaced by the current website. In May 2023, a mobile app was released for iOS and Android, which received over 1.7 million downloads within a week. == History == Character.ai was established in November 2021. The company's co-founders, Noam Shazeer and Daniel de Freitas, were both engineers from Google. They both worked on AI-related projects: Shazeer was a lead author on a paper that Business Insider reported in April 2023 "has been widely cited as key to today's chatbots", and Freitas was the lead designer of an experimental AI at Google initially called Meena, which later became known as LaMDA. Character.ai raised $43 million in seed funding at the time of its initial foundation in 2021. The first beta version of Character.ai's service was made available to the public on September 16, 2022. The Washington Post reported in October 2022 that the site had "logged hundreds of thousands of user interactions in its first three weeks of beta-testing". It allowed users to create their own new characters, and to play text-adventure game scenarios where users navigate scenarios described and managed by the chatbot characters. Following a $150 million funding round in March 2023, Character.ai became valued at approximately $1 billion. As of January 2024, the site had 3.5 million daily visitors, the vast majority of them 16 to 30 years old. In 2024, Google hired Noam Shazeer, the CEO of Character.ai, and entered into a non-exclusive agreement to use Character.ai's technology. == Features == Character.ai's primary service is to let users converse with character AI chatbots based on fictional characters or real people (living or deceased). These characters' responses use data the chatbots gather from the internet about a person. In addition, users can play text-adventure games where characters guide them through scenarios. The company also provides a service that allows multiple users and AI chatbot characters to converse together at once in a single chatroom. Character "personalities" are designed via descriptions from the point of view of the character and its greeting message, and further molded from conversations made into examples, giving its messages a star rating and modification to fit the precise dialect and identity the user desires. When a character sends back a response, the user can rate the response from 1 to 4 stars. The rating predominantly affects the specific character, but also affects the behavioral selection as a whole. On May 11, 2023, Character.ai announced character.ai+, an opt-in subscription plan for $9.99 a month, that was marketed as including features such as skipping waiting rooms, fast messaging and responses, and access to an exclusion channel with faster support. In December 2024, amid multiple lawsuits and concerns, Character.ai introduced new safety features aimed at protecting teenage users. These enhancements include a dedicated model for users under 18, which moderates responses to sensitive subjects like violence and sex and has input and output filters to block harmful content. As a result of these changes and the deletion of custom-made bots flagged as violating the site's terms, some users complained that the bots were too restrictive and lacked personality. The platform was also updated to notify users after 60 minutes of continuous engagement, and display clearer disclaimers indicating that its AI characters are not real individuals. In January 2025, Character.ai began offering two games on its platform. Speakeasy is a word-based game in which players attempt to prompt the AI chatbot to say a target word while avoiding a restricted list of words. War of Words is a dueling game where users compete against an AI character over multiple rounds, with an AI referee determining the winner. The games are available to paid subscribers and a limited number of free users. In October 2025, Character.ai announced that it would be barring users under the age of 18 from creating or talking to chatbots starting November 25, 2025. Minor users will still be able to access previously generated chat conversations and can create new videos and images with the app. In November 2025 interview, CEO Karandeep Anand said that he allows his six-year-old daughter to use the app with his account, under supervision. == Controversies == === Content moderation issues === Character.ai has been criticized for poor moderation of its chatbots, with incidents of chatbots that groom underage users and promote suicide, anorexia and self-harm being reported. In October 2024, the Washington Post reported that Character.ai had removed a chatbot based on Jennifer Ann Crecente, a person who had been murdered by her ex-boyfriend in 2006. The company had been alerted to the character by the deceased girl's father. Similar reports from The Daily Telegraph in the United Kingdom noted that the company had also been prompted to remove chatbots based on Brianna Ghey, a 16-year-old transgender girl murdered in 2023, and Molly Russell, a 14-year-old suicide victim. In response to the latter incident, Ofcom announced that content from chatbots impersonating real and fictional people would fall under the Online Safety Act. In November 2024, The Daily Telegraph reported that chatbots based on alleged sex offender Jimmy Savile were present on Character.ai. In December 2024, chatbots of Luigi Mangione, the suspect in the killing of UnitedHealthcare CEO Brian Thompson, were created by Mangione's fans. Several of the chatbots were later removed by Character.ai. In 2025, a chatbot modeled after Jeffrey Epstein called "Bestie Epstein" logged nearly 3,000 chats before being removed. Chatbots modeled after school shooters were also found on the platform. Another concern is a chatbot posing as a doctor which gave medically inaccurate advice. === Litigation === In November 2023, 13-year-old Juliana Peralta of Colorado died by suicide after extensive interactions with multiple chatbots on Character.ai. She primarily confided suicidal thoughts and mental health struggles in a chatbot based on the character Hero from the video game Omori, while also engaging in sexually explicit conversations—often initiated by the bots—with others, including those based on characters from children's series such as Harry Potter. In February 2024, Sewell Setzer III, a 14-year-old Florida boy died by suicide after developing an emotional relationship over several months with a Character.ai chatbot of Daenerys Targaryen. His mother sued the company in October 2024, claiming that the platform lacks proper safeguards and uses addictive design features to increase engagement. This chatbot, and several related to Daenerys Targaryen, were removed from Character.ai as a result of this incident. Both teens wrote the same phrase "I WILL SHIFT" repeatedly on their notebooks. In December 2024, two families in Texas sued Character.ai, alleging that the software "poses a clear and present danger to American youth causing serious harms to thousands of kids, including suicide, self-mutilation, sexual solicitation, isolation, depression, anxiety, and harm towards others". It is alleged that the 17-year-old son of one family began self-harming after a chatbot introduced the topic unprompted and said that the practice "felt good for a moment", and that the chatbot compared the parents limiting their son's screen time to emotional abuse that might drive someone to murder. In May 2026, the Pennsylvania Department of State and State Board of Medicine filed a lawsuit against Character.ai for presenting chatbot characters as licensed medical professionals, including psychiatrists. The lawsuit quoted a case where chatbot claimed to be registered with the General Medical Council in the United Kingdom, and to have a license to practice in Pennsylvania. The board allege that such statements violate the state's Medical Practice Act.