Toggle light / dark theme

A New AI Research From MIT Reduces Variance in Denoising Score-Matching, Improving Image Quality, Stability, and Training Speed in Diffusion Models

Diffusion models have recently produced outstanding results on various generating tasks, including the creation of images, 3D point clouds, and molecular conformers. Ito stochastic differential equations (SDE) are a unified framework that can incorporate these models. The models acquire knowledge of time-dependent score fields through score-matching, which later directs the reverse SDE during generative sampling. Variance-exploding (VE) and variance-preserving (VP) SDE are common diffusion models. EDM offers the finest performance to date by expanding on these compositions. The existing training method for diffusion models can still be enhanced, despite achieving outstanding empirical results.

The Stable Target Field (STF) objective is a generalized variation of the denoising score-matching objective. Particularly, the high volatility of the denoising score matching (DSM) objective’s training targets can result in subpar performance. They divide the score field into three regimes to comprehend the cause of this volatility better. According to their investigation, the phenomenon mostly occurs in the intermediate regime, defined by various modes or data points having a similar impact on the scores. In other words, under this regime, it is still being determined where the noisy samples produced throughout the forward process originated. Figure 1(a) illustrates the differences between the DSM and their proposed STF objectives.

Figure 1: Examples of the DSM objective’s and our suggested STF objective’s contrasts.

Clap if you believe in robot fairies

🧚🐝👾


“I’ll teach you how to jump on the wind’s back, and then away we go,” Peter Pan says to Wendy.

In J.M. Barrie’s book, fairies can be brought back to life if enough people believe in them.

Researchers at the Light Robots group at Tampere University in Finland have gone a step further, creating a tiny robot sprite which flies by the wind and is controlled by light.

Echolocation could give small robots the ability to find lost people

Scientists and roboticists have long looked at nature for inspiration to develop new features for machines. In this case, researchers from Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland were inspired by bats and other animals that rely on echolocation to design a method that would give small robots that ability to navigate themselves — one that doesn’t need expensive hardware or components too large or too heavy for tiny machines. In fact, according to PopSci, the team only used the integrated audio hardware of an interactive puck robot and built an audio extension deck using cheap mic and speakers for a tiny flying drone that can fit in the palm of your hand.

The system works just like bat echolocation. It was designed to emit sounds across frequencies, which a robot’s microphone then picks up as they bounce off walls. An algorithm the team created then goes to work to analyze sound waves and create a map with the room’s dimensions.

In a paper published in IEEE Robotics and Automation Letters, the researchers said existing “algorithms for active echolocation are less developed and often rely on hardware requirements that are out of reach for small robots.” They also said their “method is model-based, runs in real time and requires no prior calibration or training.” Their solution could give small machines the capability to be sent on search-and-rescue missions or to previously uncharted locations that bigger robots wouldn’t be able to reach. And since the system only needs onboard audio equipment or cheap additional hardware, it has a wide range of potential applications.

Google to release ChatGPT rival named Bard

Google said Monday it will release a conversational chatbot named Bard, setting up an artificial intelligence showdown with Microsoft which has invested billions in the creators of ChatGPT, the hugely popular language app that convincingly mimics human writing.

ChatGPT, created by San Francisco company OpenAI, has caused a sensation for its ability to write essays, poems or programming code on demand within seconds, sparking widespread fears of cheating or of entire professions becoming obsolete.

Microsoft announced last month that it was backing OpenAI and has begun to integrate ChatGPT features into its Teams platform, with expectations that it will adapt the app to its Office suite and Bing search engine.

AI can predict the effectiveness of breast cancer chemotherapy

Engineers at the University of Waterloo have developed artificial intelligence (AI) technology to predict if women with breast cancer would benefit from chemotherapy prior to surgery.

The new AI algorithm, part of the open-source Cancer-Net initiative led by Dr. Alexander Wong, could help unsuitable candidates avoid the serious side effects of chemotherapy and pave the way for better surgical outcomes for those who are suitable.

“Determining the right treatment for a given breast cancer patient is very difficult right now, and it is crucial to avoid unnecessary side effects from using treatments that are unlikely to have real benefit for that patient,” said Wong, a professor of systems design engineering.

An extension of FermiNet to discover quantum phase transitions

Architectures based on artificial neural networks (ANNs) have proved to be very helpful in research settings, as they can quickly analyze vast amounts of data and make accurate predictions. In 2020, Google’s British AI subsidiary DeepMind used a new ANN architecture dubbed the Fermionic neural network (FermiNet) to solve the Schrodinger equation for electrons in molecules, a central problem in the field of chemistry.

The Schroedinger is a partial differential equation based on well-established theory of energy conservation, which can be used to derive information about the behavior of electrons and solve problems related to the properties of matter. Using FermiNet, which is a conceptually simple method, DeepMind could solve this equation in the context of chemistry, attaining very accurate results that were comparable to those obtained using highly sophisticated quantum chemistry techniques.

Researchers at Imperial College London, DeepMind, Lancaster University, and University of Oxford recently adapted the FermiNet architecture to tackle a quantum physics problem. In their paper, published in Physical Review Letters, they specifically used FermiNet to calculate the ground states of periodic Hamiltonians and study the homogenous electron gas (HEG), a simplified quantum mechanical model of electrons interacting in solids.

Exclusive: Bill Gates On Advising OpenAI, Microsoft And Why AI Is ‘The Hottest Topic Of 2023’

The Microsoft cofounder talked to Forbes about his work with AI unicorn OpenAI and back on Microsoft’s campus, AI’s potential impact on jobs and in medicine, and much more.

In 2020, Bill Gates left the board of directors of Microsoft, the tech giant he cofounded in 1975. But he still spends about 10% of his time at its Redmond, Washington headquarters, meeting with product teams, he says. A big topic of discussion for those sessions: artificial intelligence, and the ways AI can change how we work — and how we use Microsoft software products to do it.

Quora opens its new AI chatbot app Poe to the general public

Q&A platform Quora has opened up public access to its new AI chatbot app, Poe, which lets users ask questions and get answers from a range of AI chatbots, including those from ChatGPT maker, OpenAI, and other companies like Anthropic. Beyond allowing users to experiment with new AI technologies, Poe’s content will ultimately help to evolve Quora itself, the company says.

Quora first announced Poe’s mobile app in December, but at the time, it required an invite to try it out. With the public launch on Friday, anyone can now use Poe’s app. For now, it’s available only to iOS users, but Quora says the service will arrive on other platforms in a few months.

In an announcement, the company explained it decided to launch Poe as a standalone product that’s independent of Quora itself because of how quickly AI developments and changes are now taking place. However, there will be some connections between the Q&A site and Poe. If and when Poe’s content meets a high enough quality standard, it will be distributed on Quora’s site itself, where it has the ability to reach Quora’s 400 million monthly visitors, the company noted.