Harry Shum
Generative Modeling

Harry Shum: Assisted Artistry

In 2021, I envision that the AI community will create more tools to unleash human creativity. AI will help people across the globe to communicate and express emotions and moods in their own unique ways.
Bookstack and wrapping paper
Generative Modeling

Writer’s Unblock

Neural networks for natural language processing got bigger, more prolific, and more fun to play with. Language models, which already had grown to gargantuan size, continued to swell, yielding chatbots that mimic AI luminaries and have very strange ideas about horses.
Group of people having a snowball fight and covering with a giant Facebook like button
Generative Modeling

Algorithms Against Disinformation

The worldwide pandemic and a contentious U.S. election whipped up a storm of automated disinformation, and some big AI companies reaped the whirlwind.
Dozens of snowmen with different characteristics
Generative Modeling

This Snowman Does Not Exist

While generative adversarial networks were infiltrating cultural, social, and scientific spheres, they quietly transformed the web into a bottomless well of synthetic images of . . . well, you name it.
Proof Search Tree
Generative Modeling

The Proof Is in the Network: An NLP Transformer Based on GPT that Creates Math Proofs

OpenAI’s Generative Pre-Trained Transformer (GPT) architecture has created coherent essays, images, and code. Now it generates mathematical proofs as well.
Contrast between real and real and synthetic datasets
Generative Modeling

Battling Bias in Synthetic Data

Synthetic datasets can inherit flaws in the real-world data they’re based on. Startups are working on solutions. Generating synthetic datasets for training machine learning systems is a booming business.
Series of images showing how Maxine, a media streaming platform, works
Generative Modeling

Data Compression By AI

In this work-from-home era, who hasn’t spent a video conference wishing they could read an onscreen document without turning their eyes from the person they’re talking with? Or simply hoping the stream wouldn’t stutter or stall? Deep learning can fill in the missing pieces.
Examples of AI generated images
Generative Modeling

GANs for Smaller Data

Trained on a small dataset, generative adversarial networks (GANs) tend to generate either replicas of the training data or noisy output. A new method spurs them to produce satisfying variations.
Excerpts of HBO documentary "Welcome to Chechnya"
Generative Modeling

Protected By Deepfakes

Documentary filmmakers often shield the identities of people who might be harmed for speaking out. But typical tactics like blurring faces and distorting voices can make it hard for audiences to connect emotionally. A new
Makeup applied on female faces with the help of augmented reality
Generative Modeling

A Good Look for AI

Trying on new makeup is a hassle — apply, inspect, wash off, repeat. Not to mention the tribulation of visiting brick-and-mortar stores during the pandemic. Augmented reality is helping people try on all the makeup they want without leaving home.
Data and examples related to IMLE-GAN
Generative Modeling

Making GANs More Inclusive

A typical GAN’s output doesn’t necessarily reflect the data distribution of its training set. Instead, GANs are prone to modeling the majority of the training distribution, sometimes ignoring rare attributes — say, faces that represent minority populations.
Examples of CT scans with different contrasts
Generative Modeling

More Data for Medical AI

Convolutional neural networks are good at recognizing disease symptoms in medical scans of patients who were injected with iodine-based dye, that makes their organs more visible. But some patients can’t take the dye. Now synthetic scans from a GAN are helping CNNs learn to analyze undyed images.
Data and examples related to a new technique to detect portions of an image
Generative Modeling

The Telltale Artifact

Deepfakes have gone mainstream, allowing celebrities to star in commercials without setting foot in a film studio. A new method helps determine whether such endorsements — and other images produced by generative adversarial networks — are authentic.
Examples of Generative Adversarial Networks used for image to illustration translation
Generative Modeling

Style and Substance

GANs are adept at mapping the artistic style of one picture onto the subject of another, known as style transfer. However, applied to the fanciful illustrations in children’s books, some GANs prove better at preserving style, others better at preserving subject matter.
Tennis simulator Vid2Player working
Generative Modeling

Wimbledon in a Box

Covid shut down the tennis tournament at Wimbledon this year, but a new model simulates showdowns between the sport’s greatest players. Stanford researchers developed Vid2Player, a system that simulates the footwork, positioning, and strokes of tennis pros like Roger Federer.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox