Machine Learning Research

263 Posts

Deep Learning at (Small) Scale: How to run PilotNet on a Raspberry Pi Pico microcontroller
Machine Learning Research

Deep Learning at (Small) Scale: How to run PilotNet on a Raspberry Pi Pico microcontroller

TinyML shows promise for bringing deep learning to applications where electrical power is scarce, processing in the cloud is impractical, and/or data privacy is paramount.
Text-to-3D Without 3D Training Data: How DreamFusion generates 3D images from text
Machine Learning Research

Text-to-3D Without 3D Training Data: How DreamFusion generates 3D images from text

Researchers struggle to build models that can generate a three-dimensional scene from a text prompt largely because they lack sufficient paired text-3D training examples. A new approach works without any 3D data whatsoever.
Don’t Steal My Style: Glaze tool prevents AI from learning an artist's style.
Machine Learning Research

Don’t Steal My Style: Glaze tool prevents AI from learning an artist's style.

Asked to produce “a landscape by Thomas Kinkade,” a text-to-image generator fine-tuned on the pastoral painter’s work can mimic his style in seconds, often for pennies. A new technique aims to make it harder for algorithms to mimic an artist’s style.
For Better Answers, Generate Reference Text: AI-generated reference text improves LLM output.
Machine Learning Research

For Better Answers, Generate Reference Text: AI-generated reference text improves LLM output.

If you want a model to answer questions correctly, then enriching the input with reference text retrieved from the web is a reliable way to increase the accuracy of its output. But the web isn’t necessarily the best source of reference text.
Image Generators Copy Training Data: Spotting similarities between generated images and data
Machine Learning Research

Image Generators Copy Training Data: Spotting similarities between generated images and data

We know that image generators create wonderful original works, but do they sometimes replicate their training data? Recent work found that replication does occur.
Goodbye Prompt Engineering, Hello Prompt Generation: Automatic Prompt Engineer (APE) research summary.
Machine Learning Research

Goodbye Prompt Engineering, Hello Prompt Generation: Automatic Prompt Engineer (APE) research summary.

When you’re looking for answers from a large language model, some prompts are better than others. So how can you come up with the best one? A new model automates the process.
Three Methods for Detecting Generated Text: Techniques to tell when you're reading AI-generated text
Machine Learning Research

Three Methods for Detecting Generated Text: Techniques to tell when you're reading AI-generated text

How can you tell when you’re reading machine-generated text? Three recent papers proposed solutions: Watermarking, classification, and a statistical method.
Example of interactive editing sessions with Meta's text generator PEER
Machine Learning Research

Collaborative Text Generator: A language model that collaborates with human writers

Text from current language models can be useful as a rough draft, but that leaves the polishing to human writers. A language model learned how to generate and respond to editorial directions.
Transformer-based system simulating simulate the Atari game "Pong"
Machine Learning Research

Efficient Reinforcement Learning: Reinforcement learning plus transformers equals efficiency.

Both transformers and reinforcement learning models are notoriously data-hungry. They may be less so when they work together. Vincent Micheli and colleagues at the University of Geneva trained a transformer-based system to simulate Atari games using a small amount of gameplay.
Examples of learned gaits acquired on a variety of real-world terrains
Machine Learning Research

Real-World Training on the Double: A new method rapidly trains robots in the real world.

Roboticists often train their machines in simulation, where the controller model can learn from millions of hours of experience. A new method trained robots in the real world in 20 minutes.
Vision and Language Tightly Bound: Training on a single loss function improves multimiodal AI.
Machine Learning Research

Vision and Language Tightly Bound: Training on a single loss function improves multimiodal AI.

Recent multimodal models process both text and images as sequences of tokens, but they learn to represent these distinct data types using separate loss functions. Recent work unifies the loss function as well.
GPT-4 Has Landed: Everything you need to know about GPT-4.
Machine Learning Research

GPT-4 Has Landed: Everything you need to know about GPT-4.

Get ready for the next wave of language-model mania. OpenAI introduced the latest in its GPT series of large language models to widespread excitement. The company showed statistics and examples designed to demonstrate...
Example of generation of new videos out of existing ones, using Gen-1
Machine Learning Research

Text-Driven Video Alteration: Gen-1 uses text prompts to modify videos.

On the heels of systems that generate video directly from text, new work uses text to adjust the imagery in existing videos. Researchers unveiled Gen-1...
Different illustration showing the application of PCA to color populations
Machine Learning Research

PCA Raises Red Flags: Principal component analysis can negatively impact science.

Principal component analysis is a key machine learning technique for reducing the number of dimensions in a dataset, but new research shows that its output can be inconsistent and unreliable.
Architecture for PointGoal Navigation on a legged robot
Machine Learning Research

Streamlined Robot Training: Robots trained in lo-fi simulation perform better in reality.

Autonomous robots trained to navigate in a simulation often struggle in the real world. New work helps bridge the gap in a counterintuitive way.

Subscribe to The Batch

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