Machine Learning Research

Previous systems that produce a talking-head video from a photo and a spoken-word audio clip animate the lips and other parts of the face separately.

Large language models can produce output that’s convincing but false. Researchers proposed a way to identify such hallucinations. 

The word “open” can mean many things with respect to AI. A new paper outlines the variations and ranks popular models for openness.

Published in mid-2022, DreamBooth enables Stable Diffusion to depict variations on a given subject; say, a particular dog and the same dog with angel wings or wearing a chef’s hat.

Low-rank adaptation (LoRA) reduces memory requirements when fine-tuning large language models, but it isn’t as conducive to pretraining.

The technique of model merging combines separate models into a single, more capable model without further training, but it requires expertise and manual effort. Researchers automated the process.

BERT, a large language model released in 2018 and built upon the then-new transformer architecture, marked a paradigm shift in AI.

Tool use and planning are key behaviors in agentic workflows that enable large language models (LLMs) to execute complex sequences of steps. New benchmarks measure these capabilities in common workplace tasks. 

Generative adversarial networks (GANs) produce images quickly, but they’re of relatively low quality. Diffusion image generators typically take more time, but they produce higher-quality output. Researchers aimed to achieve the best of both worlds.

A critical step in diagnosing illnesses is a conversation between doctor and patient to assemble a medical history, discuss approaches to managing symptoms, and so on.

A relatively small student LLM that learns to mimic a larger teacher model can perform nearly as well as the teacher while using much less computation. It can come even closer if the teacher also teaches reasoning techniques.

Text excerpts used in retrieval augmented generation (RAG) tend to be short. Researchers used summarization to pack more relevant context into the same amount of text.

The latest text-to-image generators can alter images in response to a text prompt, but their outputs often don’t accurately reflect the text. They do better if, in addition to a prompt, they’re told the general type of alteration they’re expected to make.

Brain-to-computer interfaces that enable users to control robots with their thoughts typically execute a single type of task such as reaching and grasping. Researchers designed a system that responds to a variety of intentions.

It’s not necessary to activate all parts of a large language model to process a given input. Using only the necessary parts saves processing.