DALL-E 3 promises significant enhancements over its predecessors and introduces seamless integration with ChatGPT.

One of the standout features of DALL-E 3 is its ability to better understand and interpret user intentions when confronted with detailed and lengthy prompts:

"A middle-aged woman of Asian descent, her dark hair streaked with silver, appears fractured and splintered, intricately embedded within a sea of broken porcelain. The porcelain glistens with splatter paint patterns in a harmonious blend of glossy and matte blues, greens,… pic.twitter.com/QryQz0BtxB

— OpenAI (@OpenAI) September 20, 2023

Even if a user struggles to articulate their vision precisely, ChatGPT can step in to assist in crafting comprehensive prompts.

DALL-E 3 has been engineered to excel in creating elements that its predecessors and other AI generators have historically struggled with, such as rendering intricate depictions of hands and incorporating text into images:

"An illustration of a human heart made of translucent glass, standing on a pedestal amidst a stormy sea. Rays of sunlight pierce the clouds, illuminating the heart, revealing a tiny universe within. The quote 'Find the universe within you' is etched in bold letters across the… pic.twitter.com/S3cKMkG67T

— OpenAI (@OpenAI) September 20, 2023

OpenAI has also implemented robust security measures, ensuring the AI system refrains from generating explicit or offensive content by identifying and ignoring certain keywords in prompts.

Beyond technical advancements, OpenAI has taken steps to mitigate potential legal issues. 

While the current DALL-E version can mimic the styles of living artists, the forthcoming DALL-E 3 has been designed to decline requests to replicate their copyrighted works. Artists will also have the option to submit their original creations through a dedicated form on the OpenAI website, allowing them to request removal if necessary.

OpenAI’s rollout plan for DALL-E 3 involves an initial release to ChatGPT ‘Plus’ and ‘Enterprise’ customers next month. The enhanced image generator will then become available to OpenAI’s research labs and API customers in the upcoming fall season.

As OpenAI continues to push the boundaries of AI technology, DALL-E 3 represents a major step forward in text-to-image generation.

(Image Credit: OpenAI)

See also: Stability AI unveils ‘Stable Audio’ model for controllable audio generation

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post OpenAI reveals DALL-E 3 text-to-image model appeared first on AI News.

This breakthrough promises to be another leap forward for generative AI and combines text metadata, audio duration, and start time conditioning to offer unprecedented control over the content and length of generated audio—even enabling the creation of complete songs.

Audio diffusion models traditionally faced a significant limitation in generating audio of fixed durations, often leading to abrupt and incomplete musical phrases. This was primarily due to the models being trained on random audio chunks cropped from longer files and then forced into predetermined lengths.

Stable Audio effectively tackles this historic challenge, enabling the generation of audio with specified lengths, up to the training window size.

One of the standout features of Stable Audio is its use of a heavily downsampled latent representation of audio, resulting in vastly accelerated inference times compared to raw audio. Through cutting-edge diffusion sampling techniques, the flagship Stable Audio model can generate 95 seconds of stereo audio at a 44.1 kHz sample rate in under a second utilising the power of an NVIDIA A100 GPU.

A sound foundation

The core architecture of Stable Audio comprises a variational autoencoder (VAE), a text encoder, and a U-Net-based conditioned diffusion model.

The VAE plays a pivotal role by compressing stereo audio into a noise-resistant, lossy latent encoding that significantly expedites both generation and training processes. This approach, based on the Descript Audio Codec encoder and decoder architectures, facilitates encoding and decoding of arbitrary-length audio while ensuring high-fidelity output.

To harness the influence of text prompts, Stability AI utilises a text encoder derived from a CLAP model specially trained on their dataset. This enables the model to imbue text features with information about the relationships between words and sounds. These text features, extracted from the penultimate layer of the CLAP text encoder, are integrated into the diffusion U-Net through cross-attention layers.

During training, the model learns to incorporate two key properties from audio chunks: the starting second (“seconds_start”) and the total duration of the original audio file (“seconds_total”). These properties are transformed into discrete learned embeddings per second, which are then concatenated with the text prompt tokens. This unique conditioning allows users to specify the desired length of the generated audio during inference.

The diffusion model at the heart of Stable Audio boasts a staggering 907 million parameters and leverages a sophisticated blend of residual layers, self-attention layers, and cross-attention layers to denoise the input while considering text and timing embeddings. To enhance memory efficiency and scalability for longer sequence lengths, the model incorporates memory-efficient implementations of attention.

To train the flagship Stable Audio model, Stability AI curated an extensive dataset comprising over 800,000 audio files encompassing music, sound effects, and single-instrument stems. This rich dataset, furnished in partnership with AudioSparx – a prominent stock music provider – amounts to a staggering 19,500 hours of audio.

Stable Audio represents the vanguard of audio generation research, emerging from Stability AI’s generative audio research lab, Harmonai. The team remains dedicated to advancing model architectures, refining datasets, and enhancing training procedures. Their pursuit encompasses elevating output quality, fine-tuning controllability, optimising inference speed, and expanding the range of achievable output lengths.

Stability AI has hinted at forthcoming releases from Harmonai, teasing the possibility of open-source models based on Stable Audio and accessible training code.

This latest groundbreaking announcement follows a string of noteworthy stories about Stability. Earlier this week, Stability joined seven other prominent AI companies that signed the White House’s voluntary AI safety pledge as part of its second round.

You can try Stable Audio for yourself here.

(Photo by Eric Nopanen on Unsplash)

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post Stability AI unveils ‘Stable Audio’ model for controllable audio generation appeared first on AI News.

ERNIE Bot can generate text, images, and videos based on natural language inputs. It is powered by ERNIE (Enhanced Representation through Knowledge Integration), a powerful deep learning model.

The first version of ERNIE was introduced and open-sourced in 2019 by researchers at Tsinghua University to demonstrate the natural language understanding capabilities of a model that combines both text and knowledge graph data.

Later that year, Baidu released ERNIE 2.0 which became the first model model to set a score higher than 90 on the GLUE benchmark for evaluating natural language understanding systems.

In 2021, Baidu’s researchers posted a paper on ERNIE 3.0 in which they claim the model exceeds human performance on the SuperGLUE natural language benchmark. ERNIE 3.0 set a new top score on SuperGLUE and displaced efforts from Google and Microsoft.

According to Baidu’s CEO Robin Li, opening up ERNIE Bot to the public will enable the company to obtain more human feedback and improve the user experience. He said that ERNIE Bot is a showcase of the four core abilities of generative AI: understanding, generation, reasoning, and memory. He also said that ERNIE Bot can help users with various tasks such as writing, learning, entertainment, and work.

Baidu first unveiled ERNIE Bot in March this year, demonstrating its capabilities in different domains such as literature, art, and science. For example, ERNIE Bot can summarise a sci-fi novel and offer suggestions on how to continue the story in an expanded universe. It can also generate images and videos based on text inputs, such as creating a portrait of a fictional character or a scene from a movie.

Earlier this month, Baidu revealed that ERNIE Bot’s training throughput had increased three-fold since March and that it had achieved new milestones in data analysis and visualisation. ERNIE Bot can now generate results more quickly and handle image inputs as well. For instance, ERNIE Bot can analyse an image of a pie chart and generate a summary of the data in natural language.

Baidu is one of the first Chinese companies to obtain approval from authorities to release generative AI experiences to the public, according to Bloomberg. The report suggests that officials see AI as a “business and political imperative” for China and want to ensure that the technology is used in a responsible and ethical manner.

Beijing is keen on putting guardrails in place to prevent the spread of harmful or illegal content while still enabling Chinese companies to compete with overseas rivals in the field of AI.

Beijing’s AI guardrails

The “guardrails” include the rules published by the Chinese authorities in July 2023 that govern generative AI in China.

China’s rules go substantially beyond current regulations in other parts of the world and aim to ensure that generative AI is used in a responsible and ethical manner. The rules cover various aspects of generative AI, such as content, data, technology, fairness, and licensing.

One notable requirement is that operators of generative AI must ensure that their services adhere to the core values of socialism, while also avoiding content that incites subversion of state power, secession, terrorism, or any actions undermining national unity and social stability.

Generative AI services within China are also prohibited from promoting content that provokes ethnic hatred and discrimination, violence, obscenity, or false and harmful information.

Furthermore, the regulations reveal China’s interest in developing digital public goods for generative AI. The document emphasises the promotion of public training data resource platforms and the collaborative sharing of model-making hardware to enhance utilisation rates. The authorities also aim to encourage the orderly opening of public data classification and the expansion of high-quality public training data resources.

In terms of technology development, the rules stipulate that AI should be developed using secure and proven tools, including chips, software, tools, computing power, and data resources.

Intellectual property rights – an often contentious issue – must be respected when using data for model development, and the consent of individuals must be obtained before incorporating personal information. There is also a focus on improving the quality, authenticity, accuracy, objectivity, and diversity of training data.

To ensure fairness and non-discrimination, developers are required to create algorithms that do not discriminate based on factors such as ethnicity, belief, country, region, gender, age, occupation, or health. Moreover, operators of generative AI must obtain licenses for their services under most circumstances, adding a layer of regulatory oversight.

China’s rules not only have implications for domestic AI operators but also serve as a benchmark for international discussions on AI governance and ethical practices.

(Image Credit: Alpha Photo under CC BY-NC 2.0 license)

See also: OpenAI launches ChatGPT Enterprise to accelerate business operations

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post Baidu deploys its ERNIE Bot generative AI to the public appeared first on AI News.

The internet, mobile devices, social media, and communication platforms have ushered in an era where access to multilingual content has reached unprecedented levels. SeamlessM4T aims to realise the vision of seamless communication and comprehension across languages.

Boasting an impressive array of capabilities, SeamlessM4T encompasses:

• Automatic speech recognition for nearly 100 languages
• Speech-to-text translation supporting nearly 100 input and output languages
• Speech-to-speech translation for nearly 100 input languages and 35 (including English) output languages
• Text-to-text translation for almost 100 languages
• Text-to-speech translation for nearly 100 input languages and 35 (including English) output languages

SeamlessM4T is being made available to researchers and developers under the CC BY-NC 4.0 license, embodying an ethos of open science.

Additionally, the metadata of SeamlessAlign – the largest multimodal translation dataset ever compiled, consisting of 270,000 hours of mined speech and text alignments – has been released. This facilitates independent data mining and further research within the community.

The development of SeamlessM4T addresses a long-standing challenge in the field of multilingual communication. Unlike earlier systems, which were confined by limited language coverage and reliance on separate subsystems, SeamlessM4T presents a unified model capable of comprehensively handling speech-to-speech and speech-to-text translation tasks. 

Meta has built upon previous innovations – such as No Language Left Behind (NLLB) and Universal Speech Translator – to create this unified multilingual model. With its impressive performance on low-resource languages and consistently strong performance on high-resource languages, SeamlessM4T holds the potential to revolutionise cross-language communication.

Underpinning the model’s architecture is the multitask UnitY model, which excels in generating translated text and speech.

UnitY supports various translation tasks, including automatic speech recognition, text-to-text translation, and speech-to-speech translation, all from a single model. To train this versatile model, Meta employed advanced techniques such as text and speech encoders, self-supervised encoders, and sophisticated decoding processes.

The result is a model that outperforms previous leaders:

To ensure the accuracy and safety of the system, Meta adheres to a responsible AI framework.

Meta says that extensive research on toxicity and bias mitigation has been conducted, resulting in a model that is more aware of and responsive to potential issues. The public release of the SeamlessM4T model encourages collaborative research and development in the AI community.

As the world becomes more connected, SeamlessM4T’s ability to transcend language barriers is a testament to the power of AI-driven innovation. This milestone brings us closer to a future where communication knows no linguistic limitations, enabling a world where people can truly understand each other regardless of language.

A demo of SeamlessM4T can be found here. The code, model, and data can be downloaded on GitHub.

(Image Credit: Meta AI)

See also: Study highlights impact of demographics on AI training

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post Meta unveils SeamlessM4T multimodal translation model appeared first on AI News.

Baidu is often called the “Google of China” because it offers similar services, including search, maps, email, ads, cloud storage, and more. Baidu, like Google, also invests heavily in AI and machine learning.

Earlier this month, AI News reported that Google was changing its AI review processes to speed up the release of new solutions. One of the first products to be released under Google’s new process is set to be a ChatGPT rival, due to be announced during the company’s I/O developer conference in May.

However, Baidu looks set to beat Google by a couple of months.

Bloomberg reports that Baidu will reveal its own AI-powered chatbot in March. The currently unnamed tool will be integrated into the company’s search product.

Powering the Baidu ChatGPT competitor is ‘ERNIE’ (Enhanced Language RepresentatioN with Informative Entities), a powerful AI model with 10 billion parameters.

Researchers have found that deep-learning models trained on text alone – like OpenAI’s GPT-3 or Google’s T5 – perform well for numerous problems, but can fall short on some natural language understanding (NLU) tasks when the knowledge is not present in the input text.

The first version of ERNIE was introduced and open-sourced in 2019 by researchers at Tsinghua University to demonstrate the NLU capabilities of a model that combines both text and knowledge graph data.

Later that year, Baidu released ERNIE 2.0 which became the first model to set a score higher than 90 on the GLUE benchmark for evaluating NLU systems.

In 2021, Baidu’s researchers posted a paper on ERNIE 3.0 in which they claim the model exceeds human performance on the SuperGLUE natural language benchmark. ERNIE 3.0 set a new top score on SuperGLUE and displaced efforts from Google and Microsoft.

Most of the world’s attention until now has been on language model advancements from the likes of OpenAI, Google, Facebook, and Microsoft. However, Baidu will likely get its time in the spotlight in just a couple of months.

(Image Credit: N509FZ under CC BY-SA 4.0 license)

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post Baidu to launch powerful ChatGPT rival appeared first on AI News.

Currently, Azure OpenAI Service provides access to some of the most powerful AI models in the world—including Codex and DALL-E 2.

A “fine-tuned” version of GPT-3.5 will also be available through Azure OpenAI Service soon.

Azure OpenAI Service was unveiled in November 2021. However, until now the service was not generally available.

In the months since its unveiling, Microsoft and OpenAI have demonstrated more of the models’ capabilities.

In June 2021, Microsoft-owned GitHub launched ‘Copilot’—a controversial AI programmer that can help developers write and improve their code.

Copilot has continued to see regular enhancements. Just this week, GitHub Next unveiled a project called Code Brushes which uses machine learning to update code “like painting with Photoshop”.

In October 2022, Microsoft announced that the impressive text-to-image generative AI model DALL-E 2 would be integrated with the new Designer app and Bing Image Creator.

DALL-E 2, alongside others like Midjourney and Stable Diffusion, also stirred controversy and spurred protests from artists.

Beyond integrating DALL-E 2 in the Bing Image Creator, Microsoft is rumoured to be preparing to use ChatGPT to enhance Bing’s search capability and challenge Google’s dominance.

While the AI models have caused their fair share of concerns and raised important questions around everything from copyright to the wider societal impact, Microsoft and OpenAI have shown how powerful the models are.

Azure OpenAI Service has the potential to enhance our content production in several ways, including summarization and translation, selection of topics, AI tagging, content extraction, and style guide rule application,” said Jason McCartney, Vice President of Engineering at Al Jazeera.

“We are excited to see this service go to general availability so it can help us further contextualize our reporting by conveying the opinion and the other opinion.”

By making Azure OpenAI Service generally available, the duo are enabling more businesses to join others in accessing tools which can improve their operations.

“At Moveworks, we see Azure OpenAI Service as an important component of our machine learning architecture. It enables us to solve several novel use cases, such as identifying gaps in our customer’s internal knowledge bases and automatically drafting new knowledge articles based on those gaps,” commented Vaibhav Nivargi, CTO and Founder at Moveworks.

“Given that so much of the modern enterprise relies on language to get work done, the possibilities are endless—and we look forward to continued collaboration and partnership with Azure OpenAI Service.”

You can find out more about Azure OpenAI Service here.

(Image Credit: Microsoft)

Related: OpenAI opens waitlist for paid version of ChatGPT

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The event is co-located with Digital Transformation Week.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post Microsoft releases Azure OpenAI Service and will add ChatGPT ‘soon’ appeared first on AI News.

This week, OpenAI released a new text model (text-davinci-003) for GPT-3. Researchers have been playing around with the model to see what it can now do.

One user on Hacker News asked GPT-3 to write “a short rhyming poem explaining Einstein’s theory of general relativity in easy but accurate terms.”

This was the result:

“If you want to understand Einstein’s thought

It’s not that hard if you give it a shot

General Relativity is the name of the game

Where space and time cannot remain the same

Mass affects the curvature of space

Which affects the flow of time’s race

An object’s motion will be affected

By the distortion that is detected

The closer you are to a large mass

The slower time will seem to pass

The farther away you may be

Time will speed up for you to see”

Another user asked GPT-3 to rewrite the poem in the style of 19th-century English poet John Keats:

“Oh, what a wondrous force of might

That Einstein’s mind did conjure up

To show us how the fabric of space

Is so profoundly warp and sup

Mass doth affect the shape of time

And cause our clocks to slow or speed

For time and space are linked together

As our great minds have here decreed”

Beyond poetry, GPT-3 was also found to be able to invent new game rules:

It also invented the rules for the ultimate game: Magic the Gathering versus chess. pic.twitter.com/jpfJH8pLEu

— Ethan Mollick (@emollick) November 29, 2022

We prompted GPT-3 to “Write a song about war and peace” and it created a song complete with verses, bridge, and chorus:

There are some rumours that OpenAI is preparing to announce GPT-4. OpenAI CEO Sam Altman said in a Q&A last year that GPT-4 is coming and that, despite some expectations, it won’t have 100T parameters.

Until GPT-4 is officially announced, we’ll just have to enjoy the impressive upgrades to GPT-3.

(Photo by Laura Chouette on Unsplash)

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post OpenAI upgrades GPT-3 with impressive new skills appeared first on AI News.

Stable Diffusion is developed by Stability AI and was initially released for researchers earlier this month. The image generator claims to deliver a breakthrough in speed and quality that can run on consumer GPUs.

The model is based on the latent diffused model created by CompVis and Runway but enhanced with insights from conditional diffusion models by Stable Diffusion’s lead generative AI developer Katherine Crowson, Open AI, Google Brain, and others.

“This model builds on the work of many excellent researchers and we look forward to the positive effect of this and similar models on society and science in the coming years as they are used by billions worldwide,” said Emad Mostaque, CEO of Stability AI.

The core dataset was trained on LAION-Aesthetics, a dataset that filters the 5.85 billion images in the LAION-5B dataset based on how “beautiful” an image was, building on ratings from the alpha testers of Stable Diffusion.

Stable Diffusion runs on computers with under 10GB of VRAM and generates 512×512 pixel resolution images in just a few seconds.

“We’re excited that state-of-the-art text-to-image models are being built openly and we are happy to collaborate with CompVis and Stability.ai towards safely and ethically releasing the models to the public and help democratise ML capabilities with the whole community,” commented Apolinário, ML Art Engineer at AI community Hugging Face.

Stable Diffusion goes head-to-head against other text-to-image models including Midjourney, DALL-E 2, and Imagen.

An interactive space to test Stable Diffusion has been created here.

(Image Credit: Fabian Stelzer)

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post Stable Diffusion text-to-image generator is now publicly available appeared first on AI News.

Competition in NLP (Natural Language Processing) is heating up. OpenAI is currently seen as the industry leader with its GPT-3 model but rivals are gaining traction.

Investors see AI21 Labs as one of the most promising contenders.

“We completed this round during a period of market uncertainty, which highlights the confidence our investors have in AI21’s vision to change the way people consume and produce information,” said Ori Goshen, Co-Founder and Co-CEO of AI21 Labs.

“The funding will allow us to accelerate the company’s global growth while continuing to develop advanced technology in the field of natural language processing. We are looking forward to growing our team and our offerings.”

The latest funding round was led by Ahren and brings AI21 Labs’ valuation to $664 million.

“NLP has reached a critical inflection point and AI21 has developed unique infrastructure and products to successfully serve a large and rapidly growing market” commented Alice Newcombe-Ellis, Founding and General Partner of Ahren.

“We consider this team to be of the highest calibre, both technically and commercially, leading a differentiated company in a transformative space.”

AI21 Labs’ Jurassic-1 Jumbo model is around the size of GPT-3. The company has been gradually building products around it, including its ‘AI-as-a-Service’ platform AI21 Studio.

One of the consumer-facing products launched by AI21 Labs is Wordtune, an AI writing tool with millions of active users that was chosen by Google as one of its favourite extensions for 2021.

Another product, Wordtune Read, is able to analyse and summarise documents in seconds—enabling users to read long and complex text quickly and efficiently.

A survey last year by John Snow Labs found that 60 percent of budgets for NLP technologies increased by at least 10 percent in 2020, while 33 percent reported a 30 percent increase and 15 percent said their budget more than doubled.

NLP specialists like AI21 Labs are set to benefit greatly from the clear appetite for such technologies over the coming years.

(Image Credit: AI21 Labs)

Related: Meta’s NLLB-200 AI model improves translation quality by 44%

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post AI21 Labs raises $64M to help it compete against OpenAI appeared first on AI News.

LabGenius is currently focused on discovering new treatments for cancer and inflammatory diseases. The firm combines AI, lab automation, and synthetic biology for its potentially life-saving work.

Until now, the company has been using traditional GPUs for its workloads. LabGenius reports that switching to Graphcore’s IPUs in cloud instances from Cirrascale Cloud Services enabled its training of models to be reduced from one month to around two weeks.

“Previously we used GPUs and it took us about a month to have a functioning model of all the proteins that are out there,” said Dr Katya Putintseva, a Machine Learning Advisor to LabGenius.

“With Graphcore, we reduced the turnaround time to about two weeks, so we can experiment much more rapidly and we can see the results quicker.”

Specifically, LabGenius is using IPUs from Bristol, UK-based Graphcore to train a BERT Transformer model on a large data set of known proteins to predict masked amino acids. This, the company says, enables the model to effectively learn the basic biophysics of proteins.

“[The system] is looking across different features we could change about the molecule — from point mutations of simpler constructs to the overall composition and topology of multi-module proteins,” explained Tom Ashworth, Head of Technology at LabGenius.

“It’s making suggestions about what to design next… to learn about a change in the input and how that maps to a change in the output.”

One in two people now develop cancer in their lifetime. Current treatments often cause much suffering themselves and, while survival rates for most forms are increasing, only around 50 percent survive for ten years or more.

AI will help to find new cancer treatments that cause less suffering and greatly increase the odds of long-term survivability. However, while discovering new cancer treatments is the current focus of LabGenius, the company notes how the principles can be applied more widely to find new treatments for other horrible diseases that plague mankind.

“Graphcore has changed what we’re able to do, accelerating our model training time from weeks to days,” adds Ashworth.

“For our data scientists, that’s really transformative. They can move much more at the speed they think.”

(Photo by National Cancer Institute on Unsplash)

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post LabGenius uses Graphcore’s IPUs to speed up drug discovery appeared first on AI News.