Machine Learning Research
LLMs Get a Life: The generative agents that mimic human behavior in a simulated town
Large language models increasingly reply to prompts with a believably human response. Can they also mimic human behavior?
Machine Learning Research
Machine Learning Research
Diffusion Transformed: A new class of diffusion models based on the transformer architecture
A tweak to diffusion models, which are responsible for most of the recent excitement about AI-generated images, enables them to produce more realistic output.
Machine Learning Research
Long-Range Weather Forecasts: This ML-based forecast simulator outperformed medium-range forecast systems.
Machine learning models have predicted weather a few days ahead of time. A new approach substantially extends the time horizon. Remi Lam and colleagues at Google developed GraphCast, a weather-forecasting system based on graph neural networks (GNNs).
Machine Learning Research
Stratego Master: DeepNash, the RL system that plays Stratego like a master
Reinforcement learning agents have mastered games like Go that provide complete information about the state of the game to players. They’ve also excelled at Texas Hold ’Em poker, which provides incomplete information, as few cards are revealed.
Machine Learning Research
Optimizer Without Hyperparameters: VeLO, the system that eliminates the need for optimizer hyperparameters
During training, a neural network usually updates its weights according to an optimizer that’s tuned using hand-picked hyperparameters. New work eliminates the need for optimizer hyperparameters.
Machine Learning Research
Sample-Efficient Training for Robots: Reinforcement learning from human feedback to train robots
Training an agent that controls a robot arm to perform a task — say, opening a door — that involves a sequence of motions (reach, grasp, turn, pull, release) can take from tens of thousands to millions of examples...
Machine Learning Research
Bug Finder: A system that provides feedback with near human-level accuracy
One challenge to making online education available worldwide is evaluating an immense volume of student work. Especially difficult is evaluating interactive computer programming assignments such as coding a game.
Machine Learning Research
Finer Tuning: Surgical fine-tuning modifies layers based on data differences.
Fine-tuning a neural network typically involves retraining every layer on new data. But research shows that networks may perform better when fine-tuning modifies only a subset of layers.
Machine Learning Research
What the Brain Sees: How a text-to-image model generates images from brain scans
A pretrained text-to-image generator enabled researchers to see — roughly — what other people looked at based on brain scans. Yu Takagi and Shinji Nishimoto developed a method that uses Stable Diffusion to reconstruct images viewed by test subjects...
Machine Learning Research
Like Diffusion but Faster: The Paella model for fast image generation, explained
The ability to generate realistic images without waiting would unlock applications from engineering to entertainment and beyond. New work takes a step in that direction.
Machine Learning Research
Optimizing Matrix Multiplication: AlphaTensor for faster matrix multiplication, explained
Matrix multiplication is executed so often in deep learning, video games, and scientific computing that even a slight acceleration can save substantial amounts of processing time. New work finds ways to speed up this crucial operation.
Machine Learning Research
Text-to-Image Editing Evolves: InstructPix2Pix for text-to-image editing, explained
Text-to-image generators like DALL·E 2, Stable Diffusion, and Adobe’s new Generative Fill feature can revise images in a targeted way — say, change the fruit in a bowl from oranges to bananas — if you enter a few words that describe the change plus an indication of the areas to be changed.