Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. The generative artificial intelligence technology is the premier product of Stability AI and is considered to be a part of the ongoing AI boom. It is primarily used to generate detailed images conditioned on text descriptions, though it can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt. Its development involved researchers from the CompVis Group at LMU Munich and Runway with a computational donation from Stability and training data from non-profit organizations. Stable Diffusion is a latent diffusion model, a kind of deep generative artificial neural network. Its code and model weights have been released publicly, and an optimized version can run on most consumer hardware equipped with a modest GPU with as little as 2.4 GB VRAM. This marked a departure from previous proprietary text-to-image models such as DALL-E and Midjourney which were accessible only via cloud services. == Development == Stable Diffusion originated from a project called Latent Diffusion, developed in Germany by researchers at LMU Munich in Munich and Heidelberg University. Four of the original 5 authors (Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz) later joined Stability AI and released subsequent versions of Stable Diffusion. The technical license for the model was released by the CompVis group at LMU Munich. Development was led by Patrick Esser of Runway and Robin Rombach of CompVis, who were among the researchers who had earlier invented the latent diffusion model architecture used by Stable Diffusion. Stability AI also credited EleutherAI and LAION (a German nonprofit which assembled the dataset on which Stable Diffusion was trained) as supporters of the project. == Technology == === Architecture === Diffusion models, introduced in 2015, are trained with the objective of removing successive applications of Gaussian noise on training images, which can be thought of as a sequence of denoising autoencoders. The name diffusion is from the thermodynamic diffusion, since they were first developed with inspiration from thermodynamics. Models in Stable Diffusion series before SD 3 all used a variant of diffusion models, called latent diffusion model (LDM), developed in 2021 by the CompVis (Computer Vision & Learning) group at LMU Munich. Stable Diffusion consists of 3 parts: the variational autoencoder (VAE), U-Net, and an optional text encoder. The VAE encoder compresses the image from pixel space to a smaller dimensional latent space, capturing a more fundamental semantic meaning of the image. Gaussian noise is iteratively applied to the compressed latent representation during forward diffusion. The U-Net block, composed of a ResNet backbone, denoises the output from forward diffusion backwards to obtain a latent representation. Finally, the VAE decoder generates the final image by converting the representation back into pixel space. The denoising step can be flexibly conditioned on a string of text, an image, or another modality. The encoded conditioning data is exposed to denoising U-Nets via a cross-attention mechanism. For conditioning on text, the fixed, pretrained CLIP ViT-L/14 text encoder is used to transform text prompts to an embedding space. Researchers point to increased computational efficiency for training and generation as an advantage of LDMs. With 860 million parameters in the U-Net and 123 million in the text encoder, Stable Diffusion is considered relatively lightweight by 2022 standards, and unlike other diffusion models, it can run on consumer GPUs, and even CPU-only if using the OpenVINO version of Stable Diffusion. ==== SD XL ==== The XL version uses the same LDM architecture as previous versions, except larger: larger UNet backbone, larger cross-attention context, two text encoders instead of one, and trained on multiple aspect ratios (not just the square aspect ratio like previous versions). The SD XL Refiner, released at the same time, has the same architecture as SD XL, but it was trained for adding fine details to preexisting images via text-conditional img2img. ==== SD 3.0 ==== The 3.0 version completely changes the backbone. Not a UNet, but a Rectified Flow Transformer, which implements the rectified flow method with a Transformer. The Transformer architecture used for SD 3.0 has three "tracks", for original text encoding, transformed text encoding, and image encoding (in latent space). The transformed text encoding and image encoding are mixed during each transformer block. The architecture is named "multimodal diffusion transformer (MMDiT), where the "multimodal" means that it mixes text and image encodings inside its operations. This differs from previous versions of DiT, where the text encoding affects the image encoding, but not vice versa. === Training data === Stable Diffusion was trained on pairs of images and captions taken from LAION-5B, a publicly available dataset derived from Common Crawl data scraped from the web, where 5 billion image-text pairs were classified based on language and filtered into separate datasets by resolution, a predicted likelihood of containing a watermark, and predicted "aesthetic" score (e.g. subjective visual quality). The dataset was created by LAION, a German non-profit which receives funding from Stability AI. The Stable Diffusion model was trained on three subsets of LAION-5B: laion2B-en, laion-high-resolution, and laion-aesthetics v2 5+. A third-party analysis of the model's training data identified that out of a smaller subset of 12 million images taken from the original wider dataset used, approximately 47% of the sample size of images came from 100 different domains, with Pinterest taking up 8.5% of the subset, followed by websites such as WordPress, Blogspot, Flickr, DeviantArt and Wikimedia Commons. An investigation by Bayerischer Rundfunk showed that LAION's datasets, hosted on Hugging Face, contain large amounts of private and sensitive data. === Training procedures === The model was initially trained on the laion2B-en and laion-high-resolution subsets, with the last few rounds of training done on LAION-Aesthetics v2 5+, a subset of 600 million captioned images which the LAION-Aesthetics Predictor V2 predicted that humans would, on average, give a score of at least 5 out of 10 when asked to rate how much they liked them. The LAION-Aesthetics v2 5+ subset also excluded low-resolution images and images which LAION-5B-WatermarkDetection identified as carrying a watermark with greater than 80% probability. Final rounds of training additionally dropped 10% of text conditioning to improve Classifier-Free Diffusion Guidance. The model was trained using 256 Nvidia A100 GPUs on Amazon Web Services for a total of 150,000 GPU-hours, at a cost of $600,000. === Limitations === Stable Diffusion has issues with degradation and inaccuracies in certain scenarios. Initial releases of the model were trained on a dataset that consists of 512×512 resolution images, meaning that the quality of generated images noticeably degrades when user specifications deviate from its "expected" 512×512 resolution; the version 2.0 update of the Stable Diffusion model later introduced the ability to natively generate images at 768×768 resolution. Another challenge is in generating human limbs due to poor data quality of limbs in the LAION database. The model is insufficiently trained to replicate human limbs and faces due to the lack of representative features in the database, and prompting the model to generate images of such type can confound the model. In addition to human limbs, Stable Diffusion is unable to generate legible ambigrams and some other forms of text and typography. Stable Diffusion XL (SDXL) version 1.0, released in July 2023, introduced native 1024x1024 resolution and improved generation for limbs and text. Accessibility for individual developers can also be a problem. In order to customize the model for new use cases that are not included in the dataset, such as generating anime characters ("waifu diffusion"), new data and further training are required. Fine-tuned adaptations of Stable Diffusion created through additional retraining have been used for a variety of different use-cases, from medical imaging to algorithmically generated music. However, this fine-tuning process is sensitive to the quality of new data; low resolution images or different resolutions from the original data can not only fail to learn the new task but degrade the overall performance of the model. Even when the model is additionally trained on high quality images, it is difficult for individuals to run models in consumer electronics. For example, the training process for waifu-diffusion requires a minimum 30 GB of VRAM, which exceeds the usual resource provided in such consumer GPUs as Nvidia's GeForce 30 series, w
Texture filtering
In computer graphics, texture filtering or texture smoothing is the method used to determine the texture color for a texture mapped pixel, using the colors of nearby texels (ie. pixels of the texture). Filtering describes how a texture is applied at many different shapes, size, angles and scales. Depending on the chosen filter algorithm, the result will show varying degrees of blurriness, detail, spatial aliasing, temporal aliasing and blocking. Depending on the circumstances, filtering can be performed in software (such as a software rendering package) or in hardware, eg. with either real time or GPU accelerated rendering circuits, or in a mixture of both. For most common interactive graphical applications, modern texture filtering is performed by dedicated hardware which optimizes memory access through memory cacheing and pre-fetch, and implements a selection of algorithms available to the user and developer. There are two main categories of texture filtering: magnification filtering and minification filtering. Depending on the situation, texture filtering is either a type of reconstruction filter where sparse data is interpolated to fill gaps (magnification), or a type of anti-aliasing (AA) where texture samples exist at a higher frequency than required for the sample frequency needed for texture fill (minification). There are many methods of texture filtering, which make different trade-offs between computational complexity, memory bandwidth and image quality. == The need for filtering == During the texture mapping process for any arbitrary 3D surface, a texture lookup takes place to find out where on the texture each pixel center falls. For texture-mapped polygonal surfaces composed of triangles typical of most surfaces in 3D games and movies, every pixel (or subordinate pixel sample) of that surface will be associated with some triangle(s) and a set of barycentric coordinates, which are used to provide a position within a texture. Such a position may not lie perfectly on the "pixel grid," necessitating some function to account for these cases. In other words, since the textured surface may be at an arbitrary distance and orientation relative to the viewer, one pixel does not usually correspond directly to one texel. Some form of filtering has to be applied to determine the best color for the pixel. Insufficient or incorrect filtering will show up in the image as artifacts (errors in the image), such as 'blockiness', jaggies, or shimmering. There can be different types of correspondence between a pixel and the texel/texels it represents on the screen. These depend on the position of the textured surface relative to the viewer, and different forms of filtering are needed in each case. Given a square texture mapped on to a square surface in the world, at some viewing distance the size of one screen pixel is exactly the same as one texel. Closer than that, the texels are larger than screen pixels, and need to be scaled up appropriately — a process known as texture magnification. Farther away, each texel is smaller than a pixel, and so one pixel covers multiple texels. In this case an appropriate color has to be picked based on the covered texels, via texture minification. Graphics APIs such as OpenGL allow the programmer to set different choices for minification and magnification filters. Note that even in the case where the pixels and texels are exactly the same size, one pixel will not necessarily match up exactly to one texel. It may be misaligned or rotated, and cover parts of up to four neighboring texels. Hence some form of filtering is still required. == Mipmapping == Mipmapping is a standard technique used to save some of the filtering work needed during texture minification. It is also highly beneficial for cache coherency - without it the memory access pattern during sampling from distant textures will exhibit extremely poor locality, adversely affecting performance even if no filtering is performed. During texture magnification, the number of texels that need to be looked up for any pixel is always four or fewer; during minification, however, as the textured polygon moves farther away potentially the entire texture might fall into a single pixel. This would necessitate reading all of its texels and combining their values to correctly determine the pixel color, a prohibitively expensive operation. Mipmapping avoids this by prefiltering the texture and storing it in smaller sizes down to a single pixel. As the textured surface moves farther away, the texture being applied switches to the prefiltered smaller size. Different sizes of the mipmap are referred to as 'levels', with Level 0 being the largest size (used closest to the viewer), and increasing levels used at increasing distances. == Filtering methods == This section lists the most common texture filtering methods, in increasing order of computational cost and image quality. === Nearest-neighbor interpolation === Nearest-neighbor interpolation is the simplest and crudest filtering method — it simply uses the color of the texel closest to the pixel center for the pixel color. While simple, this results in a large number of artifacts - texture 'blockiness' during magnification, and aliasing and shimmering during minification. This method is fast during magnification but during minification the stride through memory becomes arbitrarily large and it can often be less efficient than MIP-mapping due to the lack of spatially coherent texture access and cache-line reuse. === Nearest-neighbor with mipmapping === This method still uses nearest neighbor interpolation, but adds mipmapping — first the nearest mipmap level is chosen according to distance, then the nearest texel center is sampled to get the pixel color. This reduces the aliasing and shimmering significantly during minification but does not eliminate it entirely. In doing so it improves texture memory access and cache-line reuse through avoiding arbitrarily large access strides through texture memory during rasterization. This does not help with blockiness during magnification as each magnified texel will still appear as a large rectangle. === Linear mipmap filtering === Less commonly used, OpenGL and other APIs support nearest-neighbor sampling from individual mipmaps whilst linearly interpolating the two nearest mipmaps relevant to the sample. === Bilinear filtering === In Bilinear filtering, the four nearest texels to the pixel center are sampled (at the closest mipmap level), and their colors are combined by weighted average according to distance. This removes the 'blockiness' seen during magnification, as there is now a smooth gradient of color change from one texel to the next, instead of an abrupt jump as the pixel center crosses the texel boundary. Bilinear filtering for magnification filtering is common. When used for minification it is often used with mipmapping; though it can be used without, it would suffer the same aliasing and shimmering problems as nearest-neighbor filtering when minified too much. For modest minification ratios, however, it can be used as an inexpensive hardware accelerated weighted texture supersample. The Nintendo 64 used an unusual version of bilinear filtering where only three pixels are used known as 3-point texture filtering, instead of four due to hardware optimization concerns. This introduces a noticeable "triangulation bias" in some textures. === Trilinear filtering === Trilinear filtering is a remedy to a common artifact seen in mipmapped bilinearly filtered images: an abrupt and very noticeable change in quality at boundaries where the renderer switches from one mipmap level to the next. Trilinear filtering solves this by doing a texture lookup and bilinear filtering on the two closest mipmap levels (one higher and one lower quality), and then linearly interpolating the results. This results in a smooth degradation of texture quality as distance from the viewer increases, rather than a series of sudden drops. Of course, closer than Level 0 there is only one mipmap level available, and the algorithm reverts to bilinear filtering. === Anisotropic filtering === Anisotropic filtering is the highest quality filtering available in current consumer 3D graphics cards. Simpler, "isotropic" techniques use only square mipmaps which are then interpolated using bi– or trilinear filtering. (Isotropic means same in all directions, and hence is used to describe a system in which all the maps are squares rather than rectangles or other quadrilaterals.) When a surface is at a high angle relative to the camera, the fill area for a texture will not be approximately square. Consider the common case of a floor in a game: the fill area is far wider than it is tall. In this case, none of the square maps are a good fit. The result is blurriness and/or shimmering, depending on how the fit is chosen. Anisotropic filtering corrects this by sampling the texture as a non-square shape. The goal is
Pushmeet Kohli
Pushmeet Kohli is an Indian British computer scientist and Vice President of research at Google DeepMind. At Deepmind, he heads the "Science and Strategic Initiatives Unit". He was noted by Time magazine as being one of the 100 most influential people in AI according to the Time 100 AI list. Kohli has led and supervised a number of projects including AlphaFold, a system for predicting the 3D structures of proteins; AlphaEvolve, a general-purpose evolutionary coding agent; SynthID, a system for watermarking and detecting AI-generated content; and Co-Scientist, an agent for generating and testing new scientific hypotheses. == Education == Kohli received a Bachelor of Technology (BTech) degree in Computer Science and Engineering at the National Institute of Technology, Warangal. He went on to study at Oxford Brookes University, where he earned a PhD in computer vision for research supervised by Philip Torr in 2007. == Career and research == After his PhD, Kohli was a postdoctoral associate at the Psychometric Centre, University of Cambridge. Before joining Google DeepMind, Kohli was partner scientist and director of research at Microsoft Research. His research investigates applications of machine learning and artificial intelligence. Kohli has made research contributions in the fields of computational biology, program synthesis, superoptimization, discrete optimization, and psychometrics. Notable research projects he has contributed to include: AlphaFold - breakthrough AI system for protein structure prediction AlphaEvolve - agent for code super optimization. AlphaTensor - Reinforcement learning agent for discovering new algorithms for matrix multiplication SynthID - system for watermarking AI generated images. AlphaGenome and AlphaMissense - AI models for predicting the effect of mutations in the genome AlphaCode - Competition-level code generation with AI FunSearch - Discovering algorithms using LLMs to search over program space. Neural Program Synthesis Probabilistic Programming Community based Crowdsourcing of Data for Training AI Models Behavioral analysis and personality prediction using online networks Human Pose Estimation using the Kinect Learnt Magnetic confinement control for Fusion Learnt Density Functional for solving the fractional electron problem === Awards and honours === Kohli's research in computer vision and machine learning has been recognized by a number of scientific awards and prizes. Some notable ones include: Koenderink Prize (Test of Time award) by the European Conference of Computer Vision British Machine Vision Association and Society for Pattern Recognition (BMVA) Sullivan Prize for the best PhD thesis. IEEE Mixed Augmented Reality (ISMAR) Impact Paper award Lasting Impact Award by the ACM Symposium on User Interface Software and Technology Best paper award at the International World Wide Web Conference 2014 Best paper award in the European Conference on Computer Vision (ECCV) 2010 Best paper award in the Conference on Uncertainty in Artificial Intelligence (UAI)
Quantum finite automaton
In quantum computing, quantum finite automata (QFA) or quantum state machines are a quantum analog of probabilistic automata or a Markov decision process. They provide a mathematical abstraction of real-world quantum computers. Several types of automata may be defined, including measure-once and measure-many automata. Quantum finite automata can also be understood as the quantization of subshifts of finite type, or as a quantization of Markov chains. QFAs are, in turn, special cases of geometric finite automata or topological finite automata. The automata work by receiving a finite-length string σ = ( σ 0 , σ 1 , … , σ k ) {\displaystyle \sigma =(\sigma _{0},\sigma _{1},\dots ,\sigma _{k})} of letters σ i {\displaystyle \sigma _{i}} from a finite alphabet Σ {\displaystyle \Sigma } , and assigning to each such string a probability Pr ( σ ) {\displaystyle \operatorname {Pr} (\sigma )} indicating the probability of the automaton being in an accept state; that is, indicating whether the automaton accepted or rejected the string. The languages accepted by QFAs are not the regular languages of deterministic finite automata, nor are they the stochastic languages of probabilistic finite automata. Study of these quantum languages remains an active area of research. == Informal description == There is a simple, intuitive way of understanding quantum finite automata. One begins with a graph-theoretic interpretation of deterministic finite automata (DFA). A DFA can be represented as a labelled directed graph, with states as nodes in the graph, and arrows representing state transitions. Each arrow is labelled with a possible input symbol, so that, given a specific state and an input symbol, the arrow points at the next state. One way of representing such a graph is by means of a set of adjacency matrices, with one matrix for each input symbol. In this case, a list of possible DFA states is written as a column vector. For a given input symbol, the adjacency matrix indicates how any given state (row in the state vector) will transition to the next state; a state transition is given by matrix multiplication. One needs a distinct adjacency matrix for each possible input symbol, since each input symbol can result in a different transition. The entries in the adjacency matrix must be zero's and one's. For any given column in the matrix, only one entry can be non-zero: this is the entry that indicates the next (unique) state transition. Similarly, the state of the system is a column vector, in which only one entry is non-zero: this entry corresponds to the current state of the system. Let Σ {\displaystyle \Sigma } denote the set of input symbols. For a given input symbol α ∈ Σ {\displaystyle \alpha \in \Sigma } , write U α {\displaystyle U_{\alpha }} as the adjacency matrix that describes the evolution of the DFA to its next state. The set { U α | α ∈ Σ } {\displaystyle \{U_{\alpha }|\alpha \in \Sigma \}} then completely describes the state transition function of the DFA. Let Q represent the set of possible states of the DFA. If there are N states in Q, then each matrix U α {\displaystyle U_{\alpha }} is N by N-dimensional. The initial state q 0 ∈ Q {\displaystyle q_{0}\in Q} corresponds to a column vector with a one in the q0'th row. A general state q is then a column vector with a one in the q'th row. By abuse of notation, let q0 and q also denote these two vectors. Then, after reading input symbols α β γ ⋯ {\displaystyle \alpha \beta \gamma \cdots } from the input tape, the state of the DFA will be given by q = ⋯ U γ U β U α q 0 . {\displaystyle q=\cdots U_{\gamma }U_{\beta }U_{\alpha }q_{0}.} The state transitions are given by ordinary matrix multiplication (that is, multiply q0 by U α {\displaystyle U_{\alpha }} , etc.); the order of application is 'reversed' only because we follow the standard notation of linear algebra. The above description of a DFA, in terms of linear operators and vectors, almost begs for generalization, by replacing the state-vector q by some general vector, and the matrices { U α } {\displaystyle \{U_{\alpha }\}} by some general operators. This is essentially what a QFA does: it replaces q by a unit vector, and the { U α } {\displaystyle \{U_{\alpha }\}} by unitary matrices. Other, similar generalizations also become obvious: the vector q can be some distribution on a manifold; the set of transition matrices become automorphisms of the manifold; this defines a topological finite automaton. Similarly, the matrices could be taken as automorphisms of a homogeneous space; this defines a geometric finite automaton. Before moving on to the formal description of a QFA, there are two noteworthy generalizations that should be mentioned and understood. The first is the non-deterministic finite automaton (NFA). In this case, the vector q is replaced by a vector that can have more than one entry that is non-zero. Such a vector then represents an element of the power set of Q; it’s just an indicator function on Q. Likewise, the state transition matrices { U α } {\displaystyle \{U_{\alpha }\}} are defined in such a way that a given column can have several non-zero entries in it. Equivalently, the multiply-add operations performed during component-wise matrix multiplication should be replaced by Boolean and-or operations so that the semantics are kept intact. A well-known theorem states that, for each DFA, there is an equivalent NFA, and vice versa. This implies that the set of languages that can be recognized by DFA's and NFA's are the same; these are the regular languages. In the generalization to QFAs, the set of recognized languages will be different to the regular languages. Describing that set is one of the outstanding research problems in QFA theory. Another generalization that should be immediately apparent is to use a stochastic matrix for the transition matrices, and a probability vector for the state; this gives a probabilistic finite automaton. The entries in the state vector must be real numbers, positive, and sum to one, in order for the state vector to be interpreted as a probability. The transition matrices must preserve this property: this is why they must be stochastic. Each state vector should be imagined as specifying a point in a simplex; thus, this is a topological automaton, with the simplex being the manifold, and the stochastic matrices being linear automorphisms of the simplex onto itself. Since each transition is (essentially) independent of the previous (if we disregard the distinction between accepted and rejected languages), the PFA essentially becomes a kind of Markov chain. By contrast, in a QFA, the manifold is complex projective space C P N {\displaystyle \mathbb {C} P^{N}} , and the transition matrices are unitary matrices. Each point in C P N {\displaystyle \mathbb {C} P^{N}} corresponds to a (pure) quantum-mechanical state; the unitary matrices can be thought of as governing the time evolution of the system (viz in the Schrödinger picture). The generalization from pure states to mixed states should be straightforward: A mixed state is simply a measure-theoretic probability distribution on C P N {\displaystyle \mathbb {C} P^{N}} . A worthy point to contemplate is the distributions that result on the manifold during the input of a language. In order for an automaton to be 'efficient' in recognizing a language, that distribution should be 'as uniform as possible'. This need for uniformity is the underlying principle behind maximum entropy methods: these simply guarantee crisp, compact operation of the automaton. Put in other words, the machine learning methods used to train hidden Markov models generalize to QFAs as well: the Viterbi algorithm and the forward–backward algorithm generalize readily to the QFA. Although the study of QFA was popularized in the work of Kondacs and Watrous in 1997 and later by Moore and Crutchfeld, they were described as early as 1971, by Ion Baianu. == Measure-once automata == Measure-once automata were introduced by Cris Moore and James P. Crutchfield. They may be defined formally as follows. As with an ordinary finite automaton, the quantum automaton is considered to have N {\displaystyle N} possible internal states, represented in this case by an N {\displaystyle N} -level qudit | ψ ⟩ {\displaystyle |\psi \rangle } . More precisely, the N {\displaystyle N} -level qudit | ψ ⟩ ∈ P ( C N ) {\displaystyle |\psi \rangle \in P(\mathbb {C} ^{N})} is an element of ( N − 1 ) {\displaystyle (N-1)} -dimensional complex projective space, carrying an inner product ‖ ⋅ ‖ {\displaystyle \Vert \cdot \Vert } that is the Fubini–Study metric. The state transitions, transition matrices or de Bruijn graphs are represented by a collection of N × N {\displaystyle N\times N} unitary matrices U α {\displaystyle U_{\alpha }} , with one unitary matrix for each letter α ∈ Σ {\displaystyle \alpha \in \Sigma } . That is, given an input letter α {\displaystyle \alpha } , the unitary matrix describe
CarPlay
CarPlay is an Apple standard that enables a car radio or automotive head unit to be a display and controller for an iOS device. It is available on iPhone 5 and later models running iOS 7.1 or later. More than 800 car and motorcycle models support CarPlay, according to Apple. Vehicle owners can add support by installing certain aftermarket vehicle audio products. Most CarPlay systems connect to iOS through USB, some are wireless, and wireless support can be added through aftermarket dongles. CarPlay Ultra, a more integrated version of CarPlay, was first announced on Aston Martin DBX707 in May 2025. == Software == Apple's CarPlay-enabled apps include: Phone Apple Music Apple Maps Calendar Messages Audiobooks (part of Apple Books) Podcasts Settings News Developers must obtain permission from Apple to develop CarPlay-enabled apps. Such apps fall into five categories: Audio: primarily provide audio content, such as music or podcasts. Examples: Amazon Music, Audible, Google Play Music, iHeartRadio, QQ Music, Spotify, and Overcast. Navigation: turn-by-turn guidance, including searching for points of interests and navigating to a destination. Examples: AutoNavi, Baidu Maps, Google Maps, ChargeFinder and Waze. Automaker-made apps allow a user to control vehicle-specific features such as climate controls, gas levels, or radio via CarPlay. Messaging/Voice over IP (VoIP): listen to new messages and reply using dictation in an audio-only interface. Messaging apps on CarPlay integrate with third-party Siri support (known as SiriKit), while VoIP apps integrate with the iOS calling interface using CallKit. Examples: Telegram, WhatsApp, and Zoom. Food-ordering and parking-services apps. To discourage distracted driving, Siri is used extensively, providing voice turn-by-turn navigation guidance and voice-input for text messages. Newscast-style weather and stock results are announced instead of displayed. Requests that bring up visual information may be blocked when the car is in gear, and most native CarPlay apps deliver audio content with minimal interaction. CarPlay-enabled apps installed on the device appear on the CarPlay home screen unless disabled by the user. The inclusion or exclusion and order of app appearance can be changed on a per-vehicle basis. == Hardware == Most of the CarPlay software runs on the connected iPhone. The CarPlay interface provides audio output and a visual display to the vehicle's infotainment system, while adapting to the vehicle's available control methods, including touch screens, rotary dials, physical buttons, steering-wheel controls, and hands-free microphones. Aftermarket head units may support CarPlay or Android Auto, and many support both platforms. === Wired CarPlay === In a wired CarPlay configuration, the iPhone connects to the vehicle or head unit via a USB cable. The USB connection supplies power to the iPhone and provides a stable data link for audio, video, and control input. Wired CarPlay is supported by a wide range of factory-installed infotainment systems and aftermarket head units. Some third-party devices marketed as wireless CarPlay adapters operate by emulating a wired CarPlay connection to the vehicle. These devices plug into the vehicle's USB port and present themselves as a wired CarPlay interface, while separately establishing a wireless connection to the iPhone. Such devices still require the vehicle or head unit to support standard (wired) CarPlay. === Wireless CarPlay === Wireless CarPlay allows the iPhone to connect to a compatible vehicle or head unit without a physical cable. During the initial pairing process, the iPhone exchanges network credentials with the CarPlay receiver over Bluetooth. Once paired, CarPlay data is transmitted over a two-way Wi-Fi connection between the phone and the vehicle. Wireless CarPlay support depends on both the vehicle or head unit hardware and the iPhone model, and is generally limited to newer factory systems and select aftermarket receivers. == History == === Predecessor === In 2008, one year after the release of the iPhone, Mercedes vehicles were first to sell an audio system incorporating both the iPod and iPhone, equipped with 30-pin iOS input jacks. The new 2008 Harman Kardon NTG 2.5 featured full audio streaming, syncing, charging and control integrated into the steering wheel controls, instrument panel, and head unit. Apple was working with Mercedes to develop iOS compatible audio systems into their cars first only a year after iPhone launch. With an Apple Lightning-to-30-pin adapter, iPhones/iPods remain backwards-compatible with the Harman Kardon 2.5 and later models. This is the earliest audio system specifically engineered for iPod/iPhone integration, which predated CarPlay and every other manufacturer incorporating iOS into vehicles. The concept of CarPlay was based on the iOS 4 feature called "iPod Out" which was produced through several years of joint development by Apple and the BMW Group's Technology Office USA. iPod Out enabled vehicles with the necessary infrastructure to "host" the analog video and audio from a supporting iOS device while receiving inputs, such as button presses and knob rotations, from a car's infotainment system, to drive the "hosted" user interface in the vehicle's built-in display. It was announced at WWDC 2010 and first shipped in BMW Group vehicles in early 2011. The BMW and Mini option was called "PlugIn" and paved the way for the first cross-OEM platforms, introducing the concept of requiring a car-specific interface for apps (as opposed to MirrorLink's simple and insufficient mirroring of what was shown on the smartphone's screen). === Development === CarPlay's codename was Stark. Apple's Eddy Cue announced it as iOS in the Car at WWDC 2013. In January 2014, it was reported that Apple's hardware-oriented corporate culture had led to release delays. iOS in the Car was then rebranded and launched as CarPlay with significant design changes at the Geneva Motor Show in March 2014 with Ferrari, Kia, Mercedes-Benz, and Volvo among the first car manufacturers. At WWDC 2022, Apple announced plans to release an all-new version of CarPlay, informally dubbed CarPlay 2. The new version was said to be able to control vehicle functions, access vehicle stats, and take over multiple vehicle screens. Officials said they planned to release it in late 2024 and that manufacturers that are planning to adopt the new CarPlay include: Audi, Acura, Ford, Honda, Infiniti, Jaguar, Land Rover, Lincoln, Mercedes-Benz, Nissan, Polestar, Porsche, Renault, and Volvo. In January 2025, amidst delays, Apple removed the planned released date from its website. On May 15, 2025, Apple announced that next-generation CarPlay, now called CarPlay Ultra, would be included with all new vehicles from Aston Martin. Existing vehicles will also be receiving CarPlay Ultra through a future software update. It is only available in the US and Canada. == Timeline == June 2013: Apple introduced iOS in the Car; an early version of CarPlay that was never publicly released, at WWDC 2013. June 2013: BMW officials announced their cars would not support iOS in the Car; they later changed their minds. November 2013: Siri Eyes Free mode was offered as a dealer-installed accessory in the US to some Honda Accord and Acura RDX & ILX models. In December, Honda offered additional integration, featuring new HondaLink services, on some US and Canada models of the Civic and the Fit. March 2014: Apple introduced CarPlay, which was renamed from iOS in the Car with significant design changes, at the 2014 Geneva Motor Show with automakers Ferrari, Mercedes-Benz and Volvo. September 2014: A Ferrari FF was the first car with a full version of CarPlay. November 2014: Hyundai announced the Sonata sedan would be their first model with available CarPlay by the end of the first quarter of 2015. January 2015: Volkswagen announced CarPlay support would be coming later in 2015 and would be either standard or available on the majority of their 2016 model year lineup. May 2015: General Motors announced CarPlay would be available starting with 14 different 2016 model year Chevrolet vehicles. July 2015: Honda announced CarPlay would be available in their vehicles starting with the 2016 Honda Accord. December 2015: Volvo implemented CarPlay in the 2016 Volvo XC90 as their first vehicle with CarPlay support. December 2015: Mercedes-Benz confirmed that CarPlay would be available starting with select 2016 model year vehicles. January 2016: Apple released a list detailing the car models which support CarPlay. January 2016: Ford announced CarPlay would be available on all 2017 Ford/Lincoln model year vehicles equipped with the Sync 3 infotainment system. January 2016: FCA (now a part of Stellantis) announced CarPlay would be available on their UConnect infotainment system starting with select 2016 model year vehicles. March 2016: Subaru announced the beginning of CarPlay and Android Auto support, st
Dental AI
Dental artificial intelligence (Dental AI) refers to the application of artificial intelligence (AI) and machine-learning methods to oral healthcare data. These systems can be used to find patterns or make predictions that can aid in diagnosis, treatment, patient communication, or practice management. == History and development == Research into AI for dentistry dates to the 1990s and 2000s, alongside early CAD/CAM and image-analysis work in dental radiology. Recent developments in deep learning, especially those involving computer vision, such as convolutional neural networks, trained on large image datasets, led to a rapid improvement in performance, as well as a move from prototype technology to productization suitable for use in dental chairs. Dental schools and continuing education programs started incorporating AI content in the 2020s. == Definition and core technologies == The dental AI software accomplishes this task by using various dental images and patient data. Dental images and data used by the dental AI software include bitewing and periapical X-rays, complete mouth X-rays, detailed 3D images, intraoral images, and the patient’s medical history. The dental AI software utilizes several core technologies in accomplishing its task of assisting the dentist. First, the dental AI software utilizes machine learning and deep learning using programs that can learn from examples. Such programs are referred to as convolutional neural network (CNN) and can detect cavities and identify bone changes related to gum disease. The dental AI software utilizes computer vision, which enables the AI software to identify and quantify important features in images and data, whether they are 2D images or 3D images. Natural language processing (NLP) is used for the AI software to understand written text and can automatically generate dental notes and communicate with the patient. Furthermore, the dental AI software utilizes predictive analytics to identify patients that are more prone to dental complications and can suggest the best intervals for checkups or future dental procedures. == Applications in dentistry == Reported clinical and operational applications include diagnostic assistance for caries and periodontal disease, treatment planning assistance, patient education overlays, quality assurance, curriculum assistance for dental education, and claims documentation. Systematic reviews continue to find image-based applications such as caries detection with some variability in study design and a need for prospective validation. == Academic research and clinical validation == Several peer-reviewed studies have measured the effectiveness of AI for applications such as interproximal caries detection and periodontal bone level assessment, showing improvements over unaided readings with a focus on bias within the dataset. The Dental AI Council found variability among clinicians for diagnosis and treatment planning, suggesting the use of a standard tool as an assist. == Industry adoption == Multiple vendors offer FDA-cleared chairside AI for dental imaging: Pearl — Received U.S. FDA 510(k) clearance for its real-time radiologic aid (“Second Opinion”) in 2022 (2D), with subsequent clearances including pediatric and CBCT (“Second Opinion 3D”). TIME gave “Second Opinion” a special mention on its Best Inventions of 2022 list. Overjet — FDA-cleared for bone-level quantification and detection/outline of caries and calculus (e.g., K210187), with additional clearances expanding capabilities. VideaHealth — Received an FDA 510(k) covering 30+ detections across common dental findings (K232384), including indications for patients ages 3 and up; trade coverage has described elements of this as the first pediatric dental-AI clearance. == Regulations == In the U.S., AI-enabled dental imaging software is generally reviewed via the FDA’s 510(k) pathway. The FDA maintains a public AI-Enabled Medical Devices List, which includes numerous medical-imaging AI tools (including dental). Specific dental clearances include Overjet (K210187), VideaHealth (K232384), and Pearl entries such as “Second Opinion 3D” (K243989).
Best AI Humanizers in 2026
Shopping for the best AI humanizer? An AI humanizer is software that uses machine learning to help you get more done — it keeps getting smarter as the underlying models improve. Pricing, accuracy, and the size of the model behind the tool are the three factors that most affect daily usefulness. Whether you are a beginner or a pro, the right AI humanizer slots into your workflow and pays for itself fast. Below we compare features, pricing, and real output so you can choose with confidence.