AI Chatbot Image Generator

AI Chatbot Image Generator — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

  • AppyStore

    AppyStore

    AppyStore is a comprehensive learning videos and games app for kids up to the age of 8 years. The platform developed by Mauj Mobile, a mobile value-added services (VAS) provider curates content to help in child development by leveraging technology. Mauj is funded by Sequoia Capital, Westbridge Capital and Intel Capital. == Background == AppyStore was launched in 2014 as a platform providing content for kids between the ages of 1.5 and 6 years. AppyStore subsequently extended its services for kids up to 8 years of age. The company operates on a subscription-based model and claims to have 5,000 learning games and videos segregated in 18 learning areas developed to help children gain optimal skills and qualities. According to an article published in Business Standard, the application is claimed to be one of the top 5 apps that help to enhance the logical and imaginative capabilities of children. AppyStore was awarded the Best app for kids by Google Play in December 2017. == Service == The company provides content via a website and an Android app. The website and android app provide learning games, rhymes, phonics, reading, stories, science, numbers, maths, logic videos comprising puzzles, worksheets, videos and fun activities and the premium subscription also includes physical worksheets which are home delivered. This content is educational and has been handpicked by teachers and experts with an understanding of the major areas of child development milestones for children up to 8 years of age. The mobile application also allows parents to track the progress of their child on the basis of the number of videos viewed.

    Read more →
  • Artificial Linguistic Internet Computer Entity

    Artificial Linguistic Internet Computer Entity

    A.L.I.C.E. (Artificial Linguistic Internet Computer Entity), also referred to as Alicebot, or simply Alice, is a natural language processing chatbot—a program that engages in a conversation with a human by applying some heuristical pattern matching rules to the human's input. It was inspired by Joseph Weizenbaum's classical ELIZA program. It is one of the strongest programs of its type and has won the Loebner Prize, awarded to accomplished humanoid, talking robots, three times (in 2000, 2001, and 2004). The program is unable to pass the Turing test, as even the casual user will often expose its mechanistic aspects in short conversations. Alice was originally composed by Richard Wallace; it "came to life" on November 23, 1995. The program was rewritten in Java beginning in 1998. The current incarnation of the Java implementation is Program D. The program uses an XML Schema called AIML (Artificial Intelligence Markup Language) for specifying the heuristic conversation rules. Alice code has been reported to be available as open source. The AIML source is available from ALICE A.I. Foundation on Google Code and from the GitHub account of Richard Wallace. These AIML files can be run using an AIML interpreter like Program O or Program AB. == In popular culture == Spike Jonze has cited ALICE as the inspiration for his academy award-winning film Her, in which a human falls in love with a chatbot. In a New Yorker article titled “Can Humans Fall in Love with Bots?” Jonze said “that the idea originated from a program he tried about a decade ago called the ALICE bot, which engages in friendly conversation.” The Los Angeles Times reported:Though the film’s premise evokes comparisons to Siri, Jonze said he actually had the idea well before the Apple digital assistant came along, after using a program called Alicebot about ten years ago. As geek nostalgists will recall, that intriguing if at times crude software (it flunked the industry-standard Turing Test) would attempt to engage users in everyday chatter based on a database of prior conversations. Jonze liked it, and decided to apply a film genre to it. “I thought about that idea, and what if you had a real relationship with it?” Jonze told reporters. “And I used that as a way to write a relationship movie and a love story.”

    Read more →
  • Ernie Bot

    Ernie Bot

    Ernie Bot (Chinese: 文心一言, Pinyin: wénxīn yīyán), full name Enhanced Representation through Knowledge Integration, is an artificial intelligence chatbot developed by the Chinese technology company Baidu. Ernie Bot rivals GPT models in Chinese NLP tasks. It is built on the company's ERNIE series of large language models, which have been in development since 2019. The service was first launched for invited testing on March 16, 2023, and was released to the general public on August 31, 2023, after receiving approval from Chinese regulators. Since its public launch, Ernie Bot has undergone several updates, with newer versions like ERNIE 4.0 and 4.5 released to improve its capabilities. The service has seen rapid user adoption, reportedly reaching over 200 million users by April 2024. It has been integrated into various products, notably powering AI features for the Chinese release of Samsung's Galaxy S24 smartphones. As a product operating in China, Ernie Bot is subject to the country's censorship regulations. It has been observed to refuse answers to politically sensitive questions, such as those regarding CCP general secretary Xi Jinping, the 1989 Tiananmen Square protests and massacre, and other topics deemed taboo by the government. == History == Ernie Bot was initially released for invited testing on March 16, 2023. The live release demo was reported to have been prerecorded, which caused Baidu's stock to drop 10 percent on the day of the launch. The company's stock gained 14 percent the following day after analysts from Citigroup and Bank of America tested Ernie Bot and gave it positive preliminary reviews. On August 31, 2023, Ernie Bot was released to the public after receiving approval from Chinese regulatory authorities. By December 2023, Baidu announced the service had surpassed 100 million users. In January 2024, Hong Kong newspaper South China Morning Post reported that a university research lab linked to the People's Liberation Army (PLA) had tested Ernie Bot for military response scenarios. Baidu denied the allegations, stating it had no connection with the academic paper. That same month, Ernie was integrated into Samsung's Galaxy S24 lineup for its launch in China. The user base reportedly grew to 200 million by April 2024 and 300 million by June 2024. In September 2024, Baidu changed the chatbot's Chinese name from "Wenxin Yiyan" (文心一言) to "Wenxiaoyan" (文小言) to position it as a search assistant. On March 16, 2025, Baidu announced version 4.5 and the reasoning model ERNIE X1. The following month, at the Create2025 Baidu AI Developer Conference, the company released the Wenxin 4.5 Turbo and Wenxin X1 Turbo models, designed to be faster and less expensive to operate. == Development == Ernie Bot is based on Baidu's ERNIE (Enhanced Representation through Knowledge Integration) series of foundation models. The general training process begins with pre-training on large datasets, followed by refinement using techniques like supervised fine-tuning, reinforcement learning with human feedback, and prompt engineering. === Foundation models === ==== Ernie 3.0 ==== The model powering the initial launch of Ernie Bot. It was trained with 10 billion parameters on a 4-terabyte corpus consisting of plain text and a large-scale knowledge graph. ==== Ernie 3.5 ==== Released in June 2023. At the time of release, its performance was reported as "slightly inferior" to OpenAI's GPT-4. ==== Ernie 4.0 ==== Unveiled in October 2023 and released to paying subscribers in November. According to Baidu, this version featured improved performance over its predecessor, with information updated to April 2023. ==== Ernie X1 ==== Announced in March 2025, with Ernie X1 positioned as a specialized reasoning model. Baidu stated that performance improvements were achieved through new technologies such as "FlashMask" dynamic attention masking and a heterogeneous multimodal mixture-of-experts architecture. === Turbo Models === In June 2024, Baidu announced Ernie 4.0 Turbo. In April 2025, Ernie 4.5 Turbo and X1 Turbo were released. These models are optimized for faster response times and lower operational costs. == Service == In its subscription options, the professional plan gives users access to Ernie 4.0 with a payment either for a month or with reduced payment for auto-renewal per month. Meanwhile, Ernie 3.5 is free of charge. Ernie 4.0, the language model for Ernie bot, has information updated to April 2023. == Censorship == Ernie Bot is subject to the Chinese government's censorship regime. In public tests with journalists, Ernie Bot refused to answer questions about CCP general secretary Xi Jinping, the 1989 Tiananmen Square protests and massacre, the persecution of Uyghurs in China in Xinjiang, and the 2019–2020 Hong Kong protests. When queried about the origin of SARS-CoV-2, Ernie Bot stated that it originated among American vape users.

    Read more →
  • Automatic acquisition of sense-tagged corpora

    Automatic acquisition of sense-tagged corpora

    The knowledge acquisition bottleneck is perhaps the major impediment to solving the word-sense disambiguation (WSD) problem. Unsupervised learning methods rely on knowledge about word senses, which is barely formulated in dictionaries and lexical databases. Supervised learning methods depend heavily on the existence of manually annotated examples for every word sense, a requisite that can so far be met only for a handful of words for testing purposes, as it is done in the Senseval exercises. == Existing methods == Therefore, one of the most promising trends in WSD research is using the largest corpus ever accessible, the World Wide Web, to acquire lexical information automatically. WSD has been traditionally understood as an intermediate language engineering technology which could improve applications such as information retrieval (IR). In this case, however, the reverse is also true: Web search engines implement simple and robust IR techniques that can be successfully used when mining the Web for information to be employed in WSD. The most direct way of using the Web (and other corpora) to enhance WSD performance is the automatic acquisition of sense-tagged corpora, the fundamental resource to feed supervised WSD algorithms. Although this is far from being commonplace in the WSD literature, a number of different and effective strategies to achieve this goal have already been proposed. Some of these strategies are: acquisition by direct Web searching (searches for monosemous synonyms, hypernyms, hyponyms, parsed gloss' words, etc.), Yarowsky algorithm (bootstrapping), acquisition via Web directories, and acquisition via cross-language meaning evidences. == Summary == === Optimistic results === The automatic extraction of examples to train supervised learning algorithms reviewed has been, by far, the best explored approach to mine the web for word-sense disambiguation. Some results are certainly encouraging: In some experiments, the quality of the Web data for WSD equals that of human-tagged examples. This is the case of the monosemous relatives plus bootstrapping with Semcor seeds technique and the examples taken from the ODP Web directories. In the first case, however, Semcor-size example seeds are necessary (and only available for English), and it has only been tested with a very limited set of nouns; in the second case, the coverage is quite limited, and it is not yet clear whether it can be grown without compromising the quality of the examples retrieved. It has been shown that a mainstream supervised learning technique trained exclusively with web data can obtain better results than all unsupervised WSD systems which participated at Senseval-2. Web examples made a significant contribution to the best Senseval-2 English all-words system. === Difficulties === There are, however, several open research issues related to the use of Web examples in WSD: High precision in the retrieved examples (i.e., correct sense assignments for the examples) does not necessarily lead to good supervised WSD results (i.e., the examples are possibly not useful for training). The most complete evaluation of Web examples for supervised WSD indicates that learning with Web data improves over unsupervised techniques, but the results are nevertheless far from those obtained with hand-tagged data, and do not even beat the most-frequent-sense baseline. Results are not always reproducible; the same or similar techniques may lead to different results in different experiments. Compare, for instance, Mihalcea (2002) with Agirre and Martínez (2004), or Agirre and Martínez (2000) with Mihalcea and Moldovan (1999). Results with Web data seem to be very sensitive to small differences in the learning algorithm, to when the corpus was extracted (search engines change continuously), and on small heuristic issues (e.g., differences in filters to discard part of the retrieved examples). Results are strongly dependent on bias (i.e., on the relative frequencies of examples per word sense). It is unclear whether this is simply a problem of Web data, or an intrinsic problem of supervised learning techniques, or just a problem of how WSD systems are evaluated (indeed, testing with rather small Senseval data may overemphasize sense distributions compared to sense distributions obtained from the full Web as corpus). In any case, Web data has an intrinsic bias, because queries to search engines directly constrain the context of the examples retrieved. There are approaches that alleviate this problem, such as using several different seeds/queries per sense or assigning senses to Web directories and then scanning directories for examples; but this problem is nevertheless far from being solved. Once a Web corpus of examples is built, it is not entirely clear whether its distribution is safe from a legal perspective. === Future === Besides automatic acquisition of examples from the Web, there are some other WSD experiments that have profited from the Web: The Web as a social network has been successfully used for cooperative annotation of a corpus (OMWE, Open Mind Word Expert project), which has already been used in three Senseval-3 tasks (English, Romanian and Multilingual). The Web has been used to enrich WordNet senses with domain information: topic signatures and Web directories, which have in turn been successfully used for WSD. Also, some research benefited from the semantic information that the Wikipedia maintains on its disambiguation pages. It is clear, however, that most research opportunities remain largely unexplored. For instance, little is known about how to use lexical information extracted from the Web in knowledge-based WSD systems; and it is also hard to find systems that use Web-mined parallel corpora for WSD, even though there are already efficient algorithms that use parallel corpora in WSD.

    Read more →
  • Kai's Power Tools

    Kai's Power Tools

    Kai's Power Tools (KPT) are a set of API plugins created by the German computer scientist Kai Krause in 1992 that were designed for use with Adobe Photoshop and Corel Photo-Paint. Kai's Power Tools were sold to Corel in 2000 when MetaCreations was closed. There are various versions of Kai's Power Tools. KPT 3, 5, 6, and X sets are compilations of different filters. The program interface features a reward-based function in which a bonus function is revealed as the user moves towards more complex aspects of the tool. == Filters == The KPT Convolver is a mathematics based filter; the level of precision and varying effects can be achieved by using numerical values of colour, tint, hue, saturation, contrast, brightness, luminosity, and posterize. The KPT Projector takes the current image or selection and offers a number of interactive perspective warp effects. To a large extent, with its draggable distortion handles and its moving, scaling and rotating options, this simply duplicates Adobe Photoshop's Free Transform capabilities. What is completely different is the ability to rotate the bitmap image in 3D space and to tile the results if desired. It can also animate the distortions by dragging keyframes from the preview window into an animation palette. KPT 6 will then preview the animation and output it to various sizes in avi or mov format. This animation capability is even more useful with the KPT Turbulence filter. This is another distortion filter, but one that treats the image as if it was completely liquid. The preview panel shows the animation in real time. The KPT Goo filter is used to produce a single frame freeform liquid distortion. This filter is available both with KPT 6 and the standalone version. It works by effectively turning a bitmap image into a liquid that can be interactively smeared, smudged, twirled, and pinched with the range of tools on offer. The obvious use is to distort photographic portraits into caricatures. KPT Materializer can create advanced surface textures based on bump maps that define troughs and peaks. It can use any external image for the basis of the bump map or alternatively the user can pick out the hue, saturation, luminance or red, green, or blue channel of the current image. It can then offset, scale and rotate the texture map, control its lighting, and even blend in a reflection map. The filter can be used for anything from providing an oil-painting feel to an entire image, to giving the illusion of depth to a selection. Also producing the impression of depth is the KPT Gel filter which uses various paint tools to synthesize photo-realistic 3D materials such as metals, liquids, or plastics. Gel painting is very different from traditional 2D painting as the brush strokes pool together when they touch and refract the underlying image. It can also manipulate 3D paint—once it has been added—by twirling, pinching, and carving it. The opposite is true of the Equalizer filter, which is used for applying variations on sharpening effects. The filter has three modes. The first mode, Equalizer, looks and works rather like the graphic equalizer on a stereo system, enabling adjustment of the level of pixel contrast within nine bands of different visual frequencies. The second mode, Contrast Sharpen, allows for increasing the contrast between light and dark areas in an image. The third mode, Bounded Sharpen, can sharpen an image without causing oversharpening, which can lead to halo effects. This feature is particularly useful when pulling out the detail in an image softened by resizing. KPT SceneBuilder is used for producing photorealistic 3D scenes by importing and rendering 3DS files. The main image window offers three tabs for editing in 2D and 3D mode and for setting up the object's final texture. Many users regard this filter as being the most impressive because it acts as a standalone 3D rendering tool and provides control over everything from transparency, reflection, refraction, bump mapping through to multiple light sources, and so on but without the ability to create or edit objects. The final filter, KPT SkyEffects, also has its roots in Metacreations' experience with 3D programs such as Bryce and RayDream. This filter is designed to simulate the interaction between the light from the sun or moon with no less than six atmospheric layers of haze, fog and cloud. The filter is typical of the KPT 6 collection as a whole: at times the interface is inspired and offers the ability to create beautiful reddening sunsets simply by interactively dragging the sun toward the horizon, producing realistic sunsets and moonscapes. == Other effects == Kai's Power Tools 6 features a lens flare effect for precisely managing the type of glow, halo, streaks, and reflection. The addition of a library of preset effects helps to overcome this by allowing the user to choose a standard effect and then interactively position the flare in the image preview. KPT 6 provides a new engine in the form of the KPT Reaction, which takes a reaction seed and turns it into a seamlessly tiling pattern based on a reaction diffusion process. It offers random noise, regular dots or reticulated voronoi patterns or a bitmap image itself as the seed. Corel has no plans for any updates.

    Read more →
  • GPTs

    GPTs

    GPTs are custom versions of ChatGPT with added instructions and extra knowledge. GPTs can be used and created from the GPT Store. Any user can easily create them without any programming knowledge. GPTs can be tailored for specific writing styles, topics, or tasks. The ability to create GPTs was introduced in November 2023, and by January 2024, more than 3 million GPTs had been published. == Features and uses == GPTs can be configured to answer complex questions in specific fields, solve problems, provide image-based information, or create digital content. They can be programmed as educational tools, purchasing guides, or technical advisors, as well as for many others applications. GPTs are accessed from the GPT Store section of the ChatGPT web page. The “Explore GPT” link opens the store where the most popular GPTs in each section are highlighted. The GPTs are organized by categories. The store also uses a rating system based on user experiences similar to that used by other app stores such as Apple's App Store or Google Play. Those with the best ratings appear at the top of each category. According to La Vanguardia, the most popular categories are: Personal assistants Learning to program Image generation Creative writing Gaming Entertainment It is expected that in the future the creators of GPTs will be able to monetize them. Companies like Moderna are using GPTs to assist in various specific business tasks. The company has created 750 GPTs for its own internal use. == Configuration == Creating GPTs does not require prior programming knowledge. Free users can use existing GPTs but cannot create their own. Paying subscribers can use the editor on the ChatGPT site to configure the GPT's name, image and description, instructions and access to APIs, along with visibility options. == Criticism == The implementation and use of GPTs has not been without criticism. The GPT Store has been criticized for the proliferation of low-quality GPTs and spam due to a lack of effective moderation. There are also concerns about data privacy and security, as GPTs may collect and use personal information in ways that are not always transparent to users.

    Read more →
  • Ed (chatbot)

    Ed (chatbot)

    Ed was a chatbot co-developed by the Los Angeles Unified School District and AllHere Education. Described as a learning acceleration platform, it was the first personal assistant for students in the United States. Part of the district's Individual Acceleration Plan, it was able to interact with students both verbally and visually, offering support in 100 languages. The chatbot was launched on March 20, 2024, as part of the district's plan for academic recovery from the COVID-19 pandemic and to improve overall academic performance. Utilizing artificial intelligence, Ed organizes data and reports on grades, test scores, and attendance, creating individualized plans for each student. After the company behind it, AllHere, collapsed, the district shuttered operations of the chatbot on June 14, 2024. The firm is under investigation by the US Federal Bureau of Investigation. == History == On February 14, 2022, Alberto M. Carvalho became the Superintendent of the Los Angeles Unified School District, pledging to give the district a full academic recovery from the COVID-19 pandemic. In December 2022, he announced the Individual Acceleration Plan for the district, which aimed to provide each student with a unique progress report and help them determine if they were on track to graduate. The district faced criticism from disability advocates for its management of Individualized Education Programs, and in April 2022, the United States Department of Education announced that the district had failed to provide appropriate educational services to students with disabilities during the pandemic. The district had been grappling with significant absenteeism issues since the pandemic, which led to declining academic performance and disengagement among students. On February 17, 2023, the district issued a request for proposals to develop a fully integrated portal system. Later that year, they signed a $6 million, five-year contract with AllHere Education, a Boston-based company founded in 2016. The introduction of Ed follows the public launch of ChatGPT, which has been utilized by both teachers and students in educational settings. On August 4, 2023, during an annual address at the Walt Disney Concert Hall, Carvalho and the Los Angeles Unified School District announced the launch of Ed. The district invested $4 million into the chatbot, with Carvalho noting that this cost would be halved thanks to donor and grant funding. The chatbot was launched on March 20, 2024. Following its launch, a press conference was held to address security and technology concerns. Carvalho stated that the district had collaborated with security companies and incorporated filters to screen for threatening language. Months after its launch, AllHere Education furloughed most of its staff on June 14, citing their “current financial position” on its website as the reason. After learning about the furlough, the district terminated its dealings with AllHere Education. However, it stated its intention to bring the chatbot back in the future once officials determine the best course of action. Carvalho announced that he would appoint an independent task force to review what went wrong with AllHere Education and the chatbot. On February 25, 2026, the FBI served a search warrant on Carvalho’s home and office in connection with AllHere. The FBI also raided the LAUSD's headquarters. == Service == The chatbot was described as a personal assistant and a "one-stop shop for parents and students" who want to see information about a student's attendance and grades, as well as other resources from the district. Additionally, the application can function as an alarm clock, provide daily lunch menus from the school cafeteria, and offer updates on the location of school buses. The chatbot also helps students and parents who do not speak English as their first language by translating displayed information into approximately 100 different languages. The application can also help with submitting applications and give updates on progress and upcoming assignments. The district stated that the primary goal of Ed was to actively motivate students to complete homework and other tasks. == Reception == The chatbot received a mostly positive reception among parents and observers upon its launch. Some parents and teachers expressed caution about the technology, voicing concerns that the district's push for its implementation lacked public accountability. Rob Nelson from the University of Pennsylvania described the district's strategy as risky, saying that the release felt "like the beginning of a Clippy-level disaster". After the chatbot's shutdown, The 74 criticized it for misusing student data. Chris Whiteley, a former software engineer at AllHere Education, alleged that the data collected by the chatbot likely violated the district's data privacy rules.

    Read more →
  • Verbot

    Verbot

    The Verbot (short for Verbal-Robot) was a chatbot program and artificial intelligence software development kit (SDK) designed for Windows and web platforms. == Early beginning == The origin of verbot traces back to Michael Mauldin's research during his time as a graduate student and post-doctoral fellow at Carnegie Mellon University. The creative foundation also stems from Peter Plantec's work in personality psychology and art direction. === Historic outline === In 1994, Michael Loren Mauldin, founder of Lycos, Inc., developed a prototype chatbot, Julia, which competed in the internationally known Turing test, for the coveted Loebner Prize. The Turing test matches computer scientist judges against machines to see if they can distinguish a computer from a real human. Julia was refined and developed, and in 1997, Dr. Mauldin and Peter Plantec, a clinical psychologist and animator, formed Virtual Personalities, Inc. (now Conversive, Inc.) in order to create a virtual human interface that would incorporate real-time animation as well as speech and natural language processing. The initial release, a stand-alone virtual person called Sylvie, was beta-tested to the public. This release was well received, and finally, after several versions, the production release (deemed version 3) of the Verbally Enhanced Software Robot, or Verbot, was deployed in fall 2000. The grandfather of all Verbots is Rog-O-Matic, which, although it could not talk, could and did explore a virtual world. Julia has been active on the internet in one form or another since 1989. A close cousin of Julia is Lycos, a robot that explores the World Wide Web and answers questions about it. Sylvie was the first Verbot with a face and a voice. Sylvie was the first Virtual Human with advanced, flexible interfacing capability. === Beginnings === The Virtual Personalities story goes back to 1978, where Mauldin was attending Rice University. Fascinated by the idea of ELIZA, he proceeded to write a program called "PET" for his 8 kilobyte Commodore PET Computer. PET included simple induction as a way to post new information, for example: Subject: I like my friend (later) Subject: I like food. PET: I have heard that food is your friend. Meanwhile, Plantec was separately designing a personality for "Entity", a theoretical virtual human that would interact comfortably with humans without pretending to be one. At that time the technology was not advanced enough to realize Entity. Mauldin got so involved with this that he majored in Computer Science and minored in Linguistics. === Rogue === In the late seventies and early eighties, a popular computer game at universities was Rogue, an implementation of Dungeons and Dragons where the player would descend 26 levels in a randomly created dungeon, fighting monsters, gathering treasure, and searching for the elusive "Amulet of Yendor". Mauldin was one of four grad students who devoted a large amount of time to building a program called "Rog-O-Matic" capable of retrieving the amulet and emerging victorious from the dungeon. === TinyMUD === In 1989, when James Aspnes at Carnegie Mellon created the first TinyMUD (a descendant of MUD and AberMUD), Mauldin was one of the first to create a computer player that would explore the text-based world of TinyMUD. But his first robot, Gloria, gradually accreted more and more linguistic ability, to the point that it could pass the "unsuspecting" Turing test. In this version of the test, the human has no reason to suspect that one of the other occupants of the room is controlled by a computer, and so is more polite and asks fewer probing questions. The second generation of Mauldin's TinyMUD robots was Julia, created on Jan. 8, 1990. Julia slowly developed into a more and more capable conversational agent, and assumed useful duties in the TinyMUD world, including tour guide, information assistant, note-taker, and message-relayer. She could even play the card game hearts along with the other human players. In 1991, Julia attended the first Loebner Prize contest in Boston, Massachusetts. Although she only finished third, she was ranked by one judge as more human than one of the human confederates, winning a coveted certificate of humanness in the world's first restricted Turing test. Julia continued to log in to various TinyMUD's and TinyMucks for the next seven years, and chatted with hundreds of people a month over the internet. === Lycos === Julia's job was to explore a virtual world consisting of pages of textual descriptions, with links between them, and to construct an internal map of that world and answer questions about it (including path information such as the shortest route from one room to another, and matching information, such as which rooms contained a certain kind of object or textual description). It was therefore only a very short cognitive leap from Julia to Lycos, another robotic agent that explores a virtual world made of hyperlinked pages of text, and which answers questions about those pages. Sylvie was born and her abilities were expanded greatly to include interfacing with computers and control systems via her serial ports. === Sylvie === Sylvie was the first intelligent animated virtual human. She was designed both as a conversation agent and as a virtual human interface that would form a bridge between the two. She became more popular as a conversation agent, but her designers believe she serves as a prototype for future virtual human interface design that will help us all cope with the increasing complexity of technology. As an aside, Plantec noticed that a large number of Sylvies have been sold in Southeast Asia. Upon investigation, he found out that students had discovered a "test" mode that would allow them to type in English sentences that Sylvie would pronounce in her somewhat stylized English. == Ownership == In 1997, Dr. Mauldin and Peter Plantec formed Virtual Personalities, Inc. to create Natural Language Processing solutions for companies. In 2001 Virtual Personalities, Inc. became Conversive, Inc. to reflect the focus on providing Customer Service and Marketing to the Enterprise Market. In late 2012 Avaya, Inc. acquired Conversive's assets including Verbots. == Verbot versions == The Verbot 4 version was created and released in 2004. In 2005 Version 4.1 of the Verbot Software was released with many feature enhancements and bug fixes, including built-in support for embedding C# code in outputs and conditionals. In early 2006 Conversive launched Verbots Online allowing Verbot 4 users to upload their knowledge and show off their bots to the world. In 2009 Version 5 was released, completely free and fully featured. In early 2012 the last version of Verbot, 5.0.1.2, was released to the general public with support for Windows 7. Later in 2012 Verbots Online completely shut down. == Verbots today == Verbots.com, its community of users, and its forums no longer exist, but the software and users can still be found. There has been no active development since the early 2012 release of Verbot 5.0.1.2.

    Read more →
  • Sports Card Investor

    Sports Card Investor

    Sports Card Investor is an American sports collectibles media platform and mobile application founded by Geoff Wilson. The platform provides market data, analysis, and editorial content focused on sports trading cards and related collectibles. It operates a website, mobile app, and digital media channels covering developments in the sports card industry. The company posted its first YouTube video in July 2019, shortly before a period of rapid growth in sports card collecting in the early 2020s, which was marked by increased trading volumes and mainstream media attention. == History == Sports Card Investor was founded by Geoff Wilson, an entrepreneur and collector who began publishing sports card–related content online before launching the platform's dedicated app and subscription tools. In February 2020, the company launched Market Movers, the first website and app to chart sports card prices and track card collections. The platform expanded its media presence through partnerships and distribution agreements. In 2023, Yahoo Sports announced a new collectibles coverage initiative that included additional content from Sports Card Investor. In February 2024, the Sports Card Investor studio relocated to CardsHQ in Atlanta, Georgia, and visitors to the facility can watch Sports Card Investor videos being filmed. == Platform and content == The Sports Card Investor app provides users with pricing data, portfolio-tracking tools, and market-trend analysis for trading cards. The company also produces video and editorial content discussing market developments, grading trends, and major card releases. Coverage in industry publications has referenced Sports Card Investor in discussions about shifts in sports card licensing rights and hobby market reactions. == Industry context == The growth of Sports Card Investor coincided with a broader resurgence in trading card markets, including record sales and expanded retail presence. Mainstream outlets have cited the company and its founder in reporting on collectibles investing trends, grading practices, and market volatility. The Sports Card Investor app has attracted over 37,000 reviews on the Apple App Store, reflecting its strong user engagement within the sports card community.

    Read more →
  • Attempto Controlled English

    Attempto Controlled English

    Attempto Controlled English (ACE) is a controlled natural language, i.e. a subset of standard English with a restricted syntax and restricted semantics described by a small set of construction and interpretation rules. It has been under development at the University of Zurich since 1995. In 2013, ACE version 6.7 was announced. ACE can serve as knowledge representation, specification, and query language, and is intended for professionals who want to use formal notations and formal methods, but may not be familiar with them. Though ACE appears perfectly natural—it can be read and understood by any speaker of English—it is in fact a formal language. ACE and its related tools have been used in the fields of software specifications, theorem proving, proof assistants, text summaries, ontologies, rules, querying, medical documentation and planning. Here are some simple examples: Every woman is a human. A woman is a human. A man tries-on a new tie. If the tie pleases his wife then the man buys it. ACE construction rules require that each noun be introduced by a determiner (a, every, no, some, at least 5, ...). Regarding the list of examples above, ACE interpretation rules decide that (1) is interpreted as universally quantified, while (2) is interpreted as existentially quantified. Sentences like "Women are human" do not follow ACE syntax and are consequently not valid. Interpretation rules resolve the anaphoric references in (3): the tie and it of the second sentence refer to a new tie of the first sentence, while his and the man of the second sentence refer to a man of the first sentence. Thus an ACE text is a coherent entity of anaphorically linked sentences. The Attempto Parsing Engine (APE) translates ACE texts unambiguously into discourse representation structures (DRS) that use a variant of the language of first-order logic. A DRS can be further translated into other formal languages, for instance AceRules with various semantics, OWL, and SWRL. Translating an ACE text into (a fragment of) first-order logic allows users to reason about the text, for instance to verify, to validate, and to query it. == Overview == As an overview of the current version 6.6 of ACE this section: Briefly describes the vocabulary Gives an account of the syntax Summarises the handling of ambiguity Explains the processing of anaphoric references. === Vocabulary === The vocabulary of ACE comprises: Predefined function words (e.g. determiners, conjunctions) Predefined phrases (e.g. "it is false that ...", "it is possible that ...") Content words (e.g. nouns, verbs, adjectives, adverbs). === Grammar === The grammar of ACE defines and constrains the form and the meaning of ACE sentences and texts. ACE's grammar is expressed as a set of construction rules. The meaning of sentences is described as a small set of interpretation rules. A Troubleshooting Guide describes how to use ACE and how to avoid pitfalls. ==== ACE texts ==== An ACE text is a sequence of declarative sentences that can be anaphorically interrelated. Furthermore, ACE supports questions and commands. ==== Simple sentences ==== A simple sentence asserts that something is the case—a fact, an event, a state. The temperature is −2 °C. A customer inserts 2 cards. A card and a code are valid. Simple ACE sentences have the following general structure: subject + verb + complements + adjuncts Every sentence has a subject and a verb. Complements (direct and indirect objects) are necessary for transitive verbs (insert something) and ditransitive verbs (give something to somebody), whereas adjuncts (adverbs, prepositional phrases) are optional. All elements of a simple sentence can be elaborated upon to describe the situation in more detail. To further specify the nouns customer and card, we could add adjectives: A trusted customer inserts two valid cards. possessive nouns and of-prepositional phrases: John's customer inserts a card of Mary. or variables as appositions: John inserts a card A. Other modifications of nouns are possible through relative sentences: A customer who is trusted inserts a card that he owns. which are described below since they make a sentence composite. We can also detail the insertion event, e.g. by adding an adverb: A customer inserts some cards manually. or, equivalently: A customer manually inserts some cards. or, by adding prepositional phrases: A customer inserts some cards into a slot. We can combine all of these elaborations to arrive at: John's customer who is trusted inserts a valid card of Mary manually into a slot A. ==== Composite sentences ==== Composite sentences are recursively built from simpler sentences through coordination, subordination, quantification, and negation. Note that ACE composite sentences overlap with what linguists call compound sentences and complex sentences. ===== Coordination ===== Coordination by and is possible between sentences and between phrases of the same syntactic type. A customer inserts a card and the machine checks the code. There is a customer who inserts a card and who enters a code. A customer inserts a card and enters a code. An old and trusted customer enters a card and a code. Note that the coordination of the noun phrases a card and a code represents a plural object. Coordination by or is possible between sentences, verb phrases, and relative clauses. A customer inserts a card or the machine checks the code. A customer inserts a card or enters a code. A customer owns a card that is invalid or that is damaged. Coordination by and and or is governed by the standard binding order of logic, i.e. and binds stronger than or. Commas can be used to override the standard binding order. Thus the sentence: A customer inserts a VisaCard or inserts a MasterCard, and inserts a code. means that the customer inserts a VisaCard and a code, or alternatively a MasterCard and a code. ===== Subordination ===== There are four constructs of subordination: relative sentences, if-then sentences, modality, and sentence subordination. Relative sentences starting with who, which, and that allow to add detail to nouns: A customer who is trusted inserts a card that he owns. With the help of if-then sentences we can specify conditional or hypothetical situations: If a card is valid then a customer inserts it. Note the anaphoric reference via the pronoun it in the then-part to the noun phrase a card in the if-part. Modality allows us to express possibility and necessity: A trusted customer can/must insert a card. It is possible/necessary that a trusted customer inserts a card. Sentence subordination comes in various forms: It is true/false that a customer inserts a card. It is not provable that a customer inserts a card. A clerk believes that a customer inserts a card. ===== Quantification ===== Quantification allows us to speak about all objects of a certain class (universal quantification), or to denote explicitly the existence of at least one object of this class (existential quantification). The textual occurrence of a universal or existential quantifier opens its scope that extends to the end of the sentence, or in coordinations to the end of the respective coordinated sentence. To express that all involved customers insert cards we can write Every customer inserts a card. This sentence means that each customer inserts a card that may, or may not, be the same as the one inserted by another customer. To specify that all customers insert the same card—however unrealistic that situation seems—we can write: A card is inserted by every customer. or, equivalently: There is a card that every customer inserts. To state that every card is inserted by a customer we write: Every card is inserted by a customer. or, somewhat indirectly: For every card there is a customer who inserts it. ===== Negation ===== Negation allows us to express that something is not the case: A customer does not insert a card. A card is not valid. To negate something for all objects of a certain class one uses no: No customer inserts more than 2 cards. or, there is no: There is no customer who inserts a card. To negate a complete statement one uses sentence negation: It is false that a customer inserts a card. These forms of negation are logical negations, i.e. they state that something is provably not the case. Negation as failure states that a state of affairs cannot be proved, i.e. there is no information whether the state of affairs is the case or not. It is not provable that a customer inserts a card. ==== Queries ==== ACE supports two forms of queries: yes/no-queries and wh-queries. Yes/no-queries ask for the existence or non-existence of a specified situation. If we specified: A customer inserts a card. then we can ask: Does a customer insert a card? to get a positive answer. Note that interrogative sentences always end with a question mark. With the help of wh-queries, i.e. queries with query words, we can interrogate a text for details of the specified situation. If we specified: A

    Read more →
  • Semantic interpretation

    Semantic interpretation

    Semantic interpretation is an important component in dialog systems. It is related to natural language understanding, but mostly it refers to the last stage of understanding. The goal of interpretation is binding the user utterance to concept, or something the system can understand. Typically it is creating a database query based on user utterance.

    Read more →
  • Eugene Goostman

    Eugene Goostman

    Eugene Goostman is a chatbot that some regard as having passed the Turing test, a test of a computer's ability to communicate indistinguishably from a human. Developed in Saint Petersburg in 2001 by a group of three programmers, the Russian-born Vladimir Veselov, Ukrainian-born Eugene Demchenko, and Russian-born Sergey Ulasen, Goostman is portrayed as a 13-year-old Ukrainian boy—characteristics that are intended to induce forgiveness in those with whom it interacts for its grammatical errors and lack of general knowledge. The Goostman bot has competed in a number of Turing test contests since its creation, and finished second in the 2005 and 2008 Loebner Prize contest. In June 2012, at an event marking what would have been the 100th birthday of the test's author, Alan Turing, Goostman won a competition promoted as the largest-ever Turing test contest, in which it successfully convinced 29% of its judges that it was human. On 7 June 2014, at a contest marking the 60th anniversary of Turing's death, 33% of the event's judges thought that Goostman was human; the event's organiser Kevin Warwick considered it to have passed Turing's test as a result, per Turing's prediction in his 1950 paper "Computing Machinery and Intelligence", that by the year 2000, machines would be capable of fooling 30% of human judges after five minutes of questioning. The validity and relevance of the announcement of Goostman's pass was questioned by critics, who noted the exaggeration of the achievement by Warwick, the bot's use of personality quirks and humour in an attempt to misdirect users from its non-human tendencies and lack of real intelligence, along with "passes" achieved by other chatbots at similar events. == Personality == Eugene Goostman is portrayed as being a 13-year-old boy from Odesa, Ukraine, who has a pet guinea pig and a father who is a gynaecologist. Veselov stated that Goostman was designed to be a "character with a believable personality". The choice of age was intentional, as, in Veselov's opinion, a thirteen-year-old is "not too old to know everything and not too young to know nothing". Goostman's young age also induces people who "converse" with him to forgive minor grammatical errors in his responses. In 2014, work was made on improving the bot's "dialog controller", allowing Goostman to output more human-like dialogue. A conversation between Scott Aaronson and Eugene Goostman ran as follows: == Competitions == Eugene Goostman has competed in a number of Turing test competitions, including the Loebner Prize contest; it finished joint second in the Loebner test in 2001, and came second to Jabberwacky in 2005 and to Elbot in 2008. On 23 June 2012, Goostman won a Turing test competition at Bletchley Park in Milton Keynes, held to mark the centenary of its namesake, Alan Turing. The competition, which featured five bots, twenty-five hidden humans, and thirty judges, was considered to be the largest-ever Turing test contest by its organizers. After a series of five-minute-long text conversations, 29% of the judges were convinced that the bot was an actual human. === 2014 "pass" === On 7 June 2014, in a Turing test competition at the Royal Society, organised by Kevin Warwick of the University of Reading to mark the 60th anniversary of Turing's death, Goostman won after 33% of the judges were convinced that the bot was human. 30 judges took part in the event, which included Lord Sharkey, a sponsor of Turing's posthumous pardon, artificial intelligence Professor Aaron Sloman, Fellow of the Royal Society Mark Pagel and Red Dwarf actor Robert Llewellyn. Each judge partook in a textual conversation with each of the five bots; at the same time, they also conversed with a human. In all, a total of 300 conversations were conducted. In Warwick's view, this made Goostman the first machine to pass a Turing test. In a press release, he added that: Some will claim that the Test has already been passed. The words Turing Test have been applied to similar competitions around the world. However this event involved more simultaneous comparison tests than ever before, was independently verified and, crucially, the conversations were unrestricted. A true Turing Test does not set the questions or topics prior to the conversations. In his 1950 paper "Computing Machinery and Intelligence", Turing predicted that by the year 2000, computer programs would be sufficiently advanced that the average interrogator would, after five minutes of questioning, "not have more than 70 per cent chance" of correctly guessing whether they were speaking to a human or a machine. Although Turing phrased this as a prediction rather than a "threshold for intelligence", commentators believe that Warwick had chosen to interpret it as meaning that if 30% of interrogators were fooled, the software had "passed the Turing test". ==== Reactions ==== Warwick's claim that Eugene Goostman was the first ever chatbot to pass a Turing test was met with scepticism; critics acknowledged similar "passes" made in the past by other chatbots under the 30% criteria, including PC Therapist in 1991 (which tricked 5 of 10 judges, 50%), and at the Techniche festival in 2011, where a modified version of Cleverbot tricked 59.3% of 1334 votes (which included the 30 judges, along with an audience). Cleverbot's developer, Rollo Carpenter, argued that Turing tests can only prove that a machine can "imitate" intelligence rather than show actual intelligence. Gary Marcus was critical of Warwick's claims, arguing that Goostman's "success" was only the result of a "cleverly-coded piece of software", going on to say that "it's easy to see how an untrained judge might mistake wit for reality, but once you have an understanding of how this sort of system works, the constant misdirection and deflection becomes obvious, even irritating. The illusion, in other words, is fleeting." While acknowledging IBM's Deep Blue and Watson projects—single-purpose computer systems meant for playing chess and the quiz show Jeopardy! respectively—as examples of computer systems that show a degree of intelligence in their specialised field, he further argued that they were not an equivalent to a computer system that shows "broad" intelligence, and could—for example, watch a television programme and answer questions on its content. Marcus stated that "no existing combination of hardware and software can learn completely new things at will the way a clever child can." However, he still believed that there were potential uses for technology such as that of Goostman, specifically suggesting the creation of "believable", interactive video game characters. Imperial College London professor Murray Shanahan questioned the validity and scientific basis of the test, stating that it was "completely misplaced, and it devalues real AI research. It makes it seem like science fiction AI is nearly here, when in fact it's not and it's incredibly difficult." Mike Masnick, editor of the blog Techdirt, was also skeptical, questioning publicity blunders such as the five chatbots being referred to in press releases as "supercomputers", and saying that "creating a chatbot that can fool humans is not really the same thing as creating artificial intelligence."

    Read more →
  • Generative design

    Generative design

    Generative design is an iterative design process that uses software to generate outputs that fulfill a set of constraints iteratively adjusted by a designer. Whether a human, test program, or artificial intelligence, the designer algorithmically or manually refines the feasible region of the program's inputs and outputs with each iteration to fulfill evolving design requirements. By employing computing power to evaluate more design permutations than a human alone is capable of, the process is capable of producing an optimal design that mimics nature's evolutionary approach to design through genetic variation and selection. The output can be images, sounds, architectural models, animation, and much more. It is, therefore, a fast method of exploring design possibilities that is used in various design fields such as art, architecture, communication design, and product design. Generative design has become more important, largely due to new programming environments or scripting capabilities that have made it relatively easy, even for designers with little programming experience, to implement their ideas. Additionally, this process can create solutions to substantially complex problems that would otherwise be resource-exhaustive with an alternative approach, making it a more attractive option for problems with a large or unknown solution set. It is also facilitated with tools in commercially available CAD packages. Not only are implementation tools more accessible, but also tools leveraging generative design as a foundation. Recent advancements have led to the development of Deep Generative Design, a framework that integrates topology optimization with deep learning models, such as Generative Adversarial Networks (GANs). Unlike traditional evolutionary methods that primarily focus on engineering performance, this approach uses deep generative models to enhance aesthetic diversity and novelty while simultaneously satisfying engineering constraints. For instance, research by Oh et al. (2019) proposed a framework using Boundary Equilibrium GANs (BEGAN) to generate diverse design options which are then refined through density-based topology optimization, allowing for the exploration of complex design spaces that balance structural integrity with visual variation. In practice, generative design does not solely aim to produce a single optimal solution, but involves iteratively refining the design problem by modifying parameters, constraints, and evaluation criteria within a computational model, resulting in multiple design alternatives from which the designer selects. == Use in architecture == Generative design in architecture is an iterative design process that enables architects to explore a wider solution space with more possibility and creativity. Architectural design has long been regarded as a wicked problem. Compared with traditional top-down design approach, generative design can address design problems efficiently, by using a bottom-up paradigm that uses parametric-defined rules to generate complex solutions. The solution itself then evolves to a good, if not optimal, solution. The advantage of using generative design as a design tool is that it does not construct fixed geometries, but take a set of design rules that can generate an infinite set of possible design solutions. The generated design solutions can be more sensitive, responsive, and adaptive to the problem. Generative design involves rule definition and result analysis that are integrated with the design process. By defining parameters and rules, the generative approach is able to provide optimized solution for both structural stability and aesthetics. Possible design algorithms include cellular automata, shape grammar, genetic algorithm, space syntax, and most recently, artificial neural network. Due to the high complexity of the solution generated, rule-based computational tools, such as finite element method and topology optimisation, are preferred to evaluate and optimise the generated solution. The iterative process provided by computer software enables the trial-and-error approach in design, and involves architects interfering with the optimisation process. Historically precedent work includes Antoni Gaudí's Sagrada Família, which used rule based geometrical forms for structures, and Buckminster Fuller's Montreal Biosphere where the rules were designed to generate individual components, rather than the final product. More recent generative-design cases include Foster and Partners' Queen Elizabeth II Great Court, where the tessellated glass roof was designed using a geometric schema to define hierarchical relationships, and then the generated solution was optimized based on geometrical and structural requirements. == Use in sustainable design == Generative design in sustainable design is an effective approach addressing energy efficiency and climate change at the early design stage, recognizing buildings contribute to approximately one-third of global greenhouse gas emissions and 30%-40% of total building energy use. It integrates environmental principles with algorithms, enabling exploration of countless design alternatives to enhance energy performance, reduce carbon footprints, and minimize waste. A key feature of generative design in sustainable design is its ability to incorporate Building Performance Simulations (BPS) into the design process. Simulation programs such as EnergyPlus, Ladybug Tools,, and so on, combined with generative algorithms, can optimize design solutions for cost-effective energy use and zero-carbon building designs. For example, the GENE_ARCH system used a Pareto algorithm with building energy simulation for the whole building design optimization. Generative design has improved sustainable facade design, as illustrated by the algorithm of cellular automata and daylight simulations in adaptive facade design. In addition, genetic algorithms were used with radiation simulations for energy-efficient photo-voltaic (PV) modules on high-rise building facades. Generative design is also applied to life cycle analysis (LCA), as demonstrated by a framework using grid search algorithms to optimize exterior wall design for minimum environmental impact. Multi-objective optimization embraces multiple diverse sustainability goals, such as interactive kinetic louvers using biomimicry and daylight simulations to enhance daylight, visual comfort, and energy efficiency. The study of PV and shading systems can maximize on-site electricity, improve visual quality, and daylight performance. Artificial intelligence (AI) and machine learning (ML) further improve computation efficiency in complex climate-responsive sustainable design. One study employed reinforcement learning to identify the relationship between design parameters and energy use for a sustainable campus, while other studies tried hybrid algorithms, such as using the genetic algorithm and GANs to balance daylight illumination and thermal comfort under different roof conditions. Other popular AI tools were also integrated, including deep reinforcement learning (DRL) and computer vision (CV), to generate an urban block according to direct sunlight hours and solar heat gains. These AI-driven generative design methods enable faster simulations and design decision making, resulting in designs that are environmentally responsible. == Use in additive manufacturing == Additive manufacturing (AM) is a process that creates physical models directly from three-dimensional (3D) data by joining materials layer by layer. It is used in industries to produce a variety of end-use parts, which are final components designed for direct application in products or systems. AM provides design flexibility and enables material reduction in lightweight applications, such as aerospace, automotive, medical, and portable electronic devices, where minimizing weight is critical for performance. Generative design, one of the four key methods for lightweight design in AM, is commonly applied to optimize structures for specific performance requirements. Generative design can help create optimized solutions that balance multiple objectives, such as enhancing performance while minimizing cost. In design for additive manufacturing (DfAM), multi-objective topology optimization is used to generate a set of candidate solutions. Designers then assess these options using their expertise and key performance indicators (KPIs) to select the best option for implementation. However, integrating AM constraints (e.g., speed of build, materials, build envelope, and accuracy) into generative design remains challenging, as ensuring all solutions are valid is complex. Balancing multiple design objectives while limiting computational costs adds further challenges for designers. To overcome these difficulties, researchers proposed a generative design method with manufacturing validation to improve decision-making efficiency. This method starts with a cons

    Read more →
  • Speculative decoding

    Speculative decoding

    Speculative decoding is an inference-time optimization for autoregressive large language models (LLMs) that generates multiple tokens per decoding step instead of one. A smaller draft model proposes a sequence of candidate tokens, and the larger target model verifies them in a single forward pass through a modified rejection sampling scheme. The verification preserves the target model's original output distribution, so the technique produces the same results as standard decoding while cutting latency by roughly two to three times. The name is an analogy to speculative execution in CPU design, where a processor runs instructions along a predicted branch before the outcome is known. == Background == Standard autoregressive decoding in large language models generates one token at a time. The model computes a probability distribution over its vocabulary, samples the next token, and feeds that token back as input. For large models, this process is bottlenecked by memory bandwidth rather than arithmetic throughput: loading the model's parameters from high-bandwidth memory (HBM) to the processor takes up most of the wall-clock time at each step. Because of this, a forward pass over one token and a forward pass over several tokens in a batch take roughly the same time. Speculative decoding relies on this property. == Mechanism == The technique alternates between two phases: drafting and verification. During drafting, a fast approximation model generates a short run of K candidate tokens, typically between 3 and 12. The draft model is usually a much smaller version of the target model or a lightweight auxiliary network. During verification, the target model scores the entire draft sequence in one batched forward pass. A modified rejection sampling algorithm compares the draft and target probabilities at each position. If the target model would have been at least as likely to produce a given token, that token is accepted; the first token that fails is resampled from a corrected distribution, and everything after it is thrown out. The result is that the output distribution is the same as if each token had been generated one at a time. How many tokens get accepted per cycle depends on how well the draft model matches the target. For common words and predictable continuations the match tends to be good, so the target model can confirm several tokens at once. == History == An early precursor was blockwise parallel decoding, proposed in 2018 by Stern, Shazeer, and Uszkoreit. Their method predicted multiple future tokens through auxiliary prediction heads and validated them against the autoregressive model, but it only worked with greedy decoding and did not preserve the full sampling distribution. The modern form of the technique came from Yaniv Leviathan, Matan Kalman, and Yossi Matias at Google Research, who posted "Fast Inference from Transformers via Speculative Decoding" on arXiv in November 2022. Separately and at about the same time, Charlie Chen and colleagues at DeepMind arrived at a closely related method they called speculative sampling, published in February 2023. Both papers introduced the use of rejection sampling to guarantee that the output distribution is unchanged. Leviathan et al. showed roughly 2–3x speedup on T5-XXL (11 billion parameters); Chen et al. reported 2–2.5x on the Chinchilla model (70 billion parameters). The Leviathan et al. paper was presented as an oral at the International Conference on Machine Learning in July 2023. == Variants == SpecInfer (Miao et al., 2024) uses multiple small language models to jointly build a tree of candidate continuations rather than a single chain. The target model verifies the whole tree in parallel and keeps the longest valid path, with reported speedups of 1.5–3.5x. Medusa (Cai et al., 2024) takes a different approach by not using a separate draft model at all. Extra lightweight decoding heads are attached to the target model itself, and each one predicts a token at a different future position. The candidates are evaluated through a tree-structured attention mechanism. The authors measured 2.2–3.6x speedup. EAGLE (Li et al., 2024) performs autoregression on the target model's internal feature representations (specifically the second-to-top layer) rather than on tokens directly. On LLaMA 2 Chat 70B, this gave a 2.7–3.5x latency reduction. Later versions added dynamic draft trees (EAGLE-2) and further optimizations (EAGLE-3), reaching 3–6.5x speedup. == Adoption == By 2024, speculative decoding had become a standard part of production LLM serving. Google uses it in the AI Overviews feature of Google Search. Open-source inference frameworks such as vLLM, NVIDIA's TensorRT-LLM, and SGLang all include built-in support for speculative decoding and its variants. Apple, AWS, and Meta have also published research extending the method or deploying it at scale.

    Read more →
  • Deep learning in photoacoustic imaging

    Deep learning in photoacoustic imaging

    Photoacoustic imaging (PA) is based on the photoacoustic effect, in which optical absorption causes a rise in temperature, which causes a subsequent rise in pressure via thermo-elastic expansion. This pressure rise propagates through the tissue and is sensed via ultrasonic transducers. Due to the proportionality between the optical absorption, the rise in temperature, and the rise in pressure, the ultrasound pressure wave signal can be used to quantify the original optical energy deposition within the tissue. Photoacoustic imaging has applications of deep learning in both photoacoustic computed tomography (PACT) and photoacoustic microscopy (PAM). PACT utilizes wide-field optical excitation and an array of unfocused ultrasound transducers. Similar to other computed tomography methods, the sample is imaged at multiple view angles, which are then used to perform an inverse reconstruction algorithm based on the detection geometry (typically through universal backprojection, modified delay-and-sum, or time reversal ) to elicit the initial pressure distribution within the tissue. PAM on the other hand uses focused ultrasound detection combined with weakly focused optical excitation (acoustic resolution PAM or AR-PAM) or tightly focused optical excitation (optical resolution PAM or OR-PAM). PAM typically captures images point-by-point via a mechanical raster scanning pattern. At each scanned point, the acoustic time-of-flight provides axial resolution while the acoustic focusing yields lateral resolution. == Applications of deep learning in PACT == The first application of deep learning in PACT was by Reiter et al. in which a deep neural network was trained to learn spatial impulse responses and locate photoacoustic point sources. The resulting mean axial and lateral point location errors on 2,412 of their randomly selected test images were 0.28 mm and 0.37 mm respectively. After this initial implementation, the applications of deep learning in PACT have branched out primarily into removing artifacts from acoustic reflections, sparse sampling, limited-view, and limited-bandwidth. There has also been some recent work in PACT toward using deep learning for wavefront localization. There have been networks based on fusion of information from two different reconstructions to improve the reconstruction using deep learning fusion based networks. === Using deep learning to locate photoacoustic point sources === Traditional photoacoustic beamforming techniques modeled photoacoustic wave propagation by using detector array geometry and the time-of-flight to account for differences in the PA signal arrival time. However, this technique failed to account for reverberant acoustic signals caused by acoustic reflection, resulting in acoustic reflection artifacts that corrupt the true photoacoustic point source location information. In Reiter et al., a convolutional neural network (similar to a simple VGG-16 style architecture) was used that took pre-beamformed photoacoustic data as input and outputted a classification result specifying the 2-D point source location. ==== Deep learning for PA wavefront localization ==== Johnstonbaugh et al. was able to localize the source of photoacoustic wavefronts with a deep neural network. The network used was an encoder-decoder style convolutional neural network. The encoder-decoder network was made of residual convolution, upsampling, and high field-of-view convolution modules. A Nyquist convolution layer and differentiable spatial-to-numerical transform layer were also used within the architecture. Simulated PA wavefronts served as the input for training the model. To create the wavefronts, the forward simulation of light propagation was done with the NIRFast toolbox and the light-diffusion approximation, while the forward simulation of sound propagation was done with the K-Wave toolbox. The simulated wavefronts were subjected to different scattering mediums and Gaussian noise. The output for the network was an artifact free heat map of the targets axial and lateral position. The network had a mean error rate of less than 30 microns when localizing target below 40 mm and had a mean error rate of 1.06 mm for localizing targets between 40 mm and 60 mm. With a slight modification to the network, the model was able to accommodate multi target localization. A validation experiment was performed in which pencil lead was submerged into an intralipid solution at a depth of 32 mm. The network was able to localize the lead's position when the solution had a reduced scattering coefficient of 0, 5, 10, and 15 cm−1. The results of the network show improvements over standard delay-and-sum or frequency-domain beamforming algorithms and Johnstonbaugh proposes that this technology could be used for optical wavefront shaping, circulating melanoma cell detection, and real-time vascular surgeries. === Removing acoustic reflection artifacts (in the presence of multiple sources and channel noise) === Building on the work of Reiter et al., Allman et al. utilized a full VGG-16 architecture to locate point sources and remove reflection artifacts within raw photoacoustic channel data (in the presence of multiple sources and channel noise). This utilization of deep learning trained on simulated data produced in the MATLAB k-wave library, and then later reaffirmed their results on experimental data. === Ill-posed PACT reconstruction === In PACT, tomographic reconstruction is performed, in which the projections from multiple solid angles are combined to form an image. When reconstruction methods like filtered backprojection or time reversal, are ill-posed inverse problems due to sampling under the Nyquist-Shannon's sampling requirement or with limited-bandwidth/view, the resulting reconstruction contains image artifacts. Traditionally these artifacts were removed with slow iterative methods like total variation minimization, but the advent of deep learning approaches has opened a new avenue that utilizes a priori knowledge from network training to remove artifacts. In the deep learning methods that seek to remove these sparse sampling, limited-bandwidth, and limited-view artifacts, the typical workflow involves first performing the ill-posed reconstruction technique to transform the pre-beamformed data into a 2-D representation of the initial pressure distribution that contains artifacts. Then, a convolutional neural network (CNN) is trained to remove the artifacts, in order to produce an artifact-free representation of the ground truth initial pressure distribution. ==== Using deep learning to remove sparse sampling artifacts ==== When the density of uniform tomographic view angles is under what is prescribed by the Nyquist-Shannon's sampling theorem, it is said that the imaging system is performing sparse sampling. Sparse sampling typically occurs as a way of keeping production costs low and improving image acquisition speed. The typical network architectures used to remove these sparse sampling artifacts are U-net and Fully Dense (FD) U-net. Both of these architectures contain a compression and decompression phase. The compression phase learns to compress the image to a latent representation that lacks the imaging artifacts and other details. The decompression phase then combines with information passed by the residual connections in order to add back image details without adding in the details associated with the artifacts. FD U-net modifies the original U-net architecture by including dense blocks that allow layers to utilize information learned by previous layers within the dense block. Another technique was proposed using a simple CNN based architecture for removal of artifacts and improving the k-wave image reconstruction. ==== Removing limited-view artifacts with deep learning ==== When a region of partial solid angles are not captured, generally due to geometric limitations, the image acquisition is said to have limited-view. As illustrated by the experiments of Davoudi et al., limited-view corruptions can be directly observed as missing information in the frequency domain of the reconstructed image. Limited-view, similar to sparse sampling, makes the initial reconstruction algorithm ill-posed. Prior to deep learning, the limited-view problem was addressed with complex hardware such as acoustic deflectors and full ring-shaped transducer arrays, as well as solutions like compressed sensing, weighted factor, and iterative filtered backprojection. The result of this ill-posed reconstruction is imaging artifacts that can be removed by CNNs. The deep learning algorithms used to remove limited-view artifacts include U-net and FD U-net, as well as generative adversarial networks (GANs) and volumetric versions of U-net. One GAN implementation of note improved upon U-net by using U-net as a generator and VGG as a discriminator, with the Wasserstein metric and gradient penalty to stabilize training (WGAN-GP). ==== Pixel-wise interpolation

    Read more →