Machine Learning Research

281 Posts

Diagram of AI cooling process on large data centers
Machine Learning Research

Energy-Efficient Cooling: Google's DeepMind algorithms dramatically boost energy efficiency in its data centers.

A reinforcement learning model maintains cooler temperatures in large data centers and other buildings.
Features from ViT showing edge, texture, pattern, part, and object detection
Machine Learning Research

How Vision Transformers See: A new understanding of what's happening inside transformers

While transformers have delivered state-of-the-art results in several domains of machine learning, few attempts have been made to probe their inner workings. Researchers offer a new approach.
Masked Pretraining for CNNs: ConvNeXt V2, the new model family that boosts ConvNet performance
Machine Learning Research

Masked Pretraining for CNNs: ConvNeXt V2, the new model family that boosts ConvNet performance

Vision transformers have bested convolutional neural networks (CNNs) in a number of key vision tasks. Have CNNs hit their limit? New research suggests otherwise.
Different Media, Similar Embeddings: ImageBind, the AI model that binds data from seven data types at once
Machine Learning Research

Different Media, Similar Embeddings: ImageBind, the AI model that binds data from seven data types at once

The ability of OpenAI’s CLIP to produce similar embeddings of a text phrase and a matching image opened up applications like classifying images according to labels that weren’t in the training set. A new model extends this capability to seven data types.
Text-To-3D Animation: MAV3D, a method for generating 3D dynamic scenes from text descriptions
Machine Learning Research

Text-To-3D Animation: MAV3D, a method for generating 3D dynamic scenes from text descriptions

Text-to-video generation is so 2022! A new system takes in text and generates an animated 3D scene that can be viewed or rendered from any angle.
Vision Transformers Made Manageable: FlexiViT, the vision transformer that allows users to specify the patch size
Machine Learning Research

Vision Transformers Made Manageable: FlexiViT, the vision transformer that allows users to specify the patch size

Vision transformers typically process images in patches of fixed size. Smaller patches yield higher accuracy but require more computation. A new training method lets AI engineers adjust the tradeoff.
LLMs Get a Life: The generative agents that mimic human behavior in a simulated town
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?
Diffusion Transformed: A new class of diffusion models based on the transformer architecture
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.
Long-Range Weather Forecasts: This ML-based forecast simulator outperformed medium-range forecast systems.
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).
Stratego Master: DeepNash, the RL system that plays Stratego like a master
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.
Optimizer Without Hyperparameters: VeLO, the system that eliminates the need for optimizer hyperparameters
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.
Sample-Efficient Training for Robots: Reinforcement learning from human feedback to train robots
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...
Bug Finder: A system that provides feedback with near human-level accuracy
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.
Finer Tuning: Surgical fine-tuning modifies layers based on data differences.
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.
What the Brain Sees: How a text-to-image model generates images from brain scans
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...
Load More

Subscribe to The Batch

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