Machine Learning Research

Traditionally, building 3D meshes for gaming, animation, product design, architecture, and the like has been labor-intensive. Now the ability to generate 3D meshes from a single image is widely available.

Datasets that were scraped from the web tend to be unbalanced, meaning examples of some classes (say, cats) are plentiful while examples of others (say, caterpillars) are scarce.

Researchers have probed the inner workings of individual layers of large language models. A new tool applies this approach to all layers.

How often do large language models make up information when they generate text based on a retrieved document? A study evaluated the tendency of popular models to hallucinate while performing retrieval-augmented generation (RAG). 

A new model generates tokens faster than current transformers, especially when processing long inputs.

Researchers introduced a model that handles an unprecedented number of input and output types, including many related to performing computer vision tasks.

An agentic coding assistant boosted the state of the art in an important benchmark by more than 30 percent.

When training vision-language models, developers often remove lower-quality examples from the training set. But keeping only the highest-quality examples may not be ideal, researchers found.

Alibaba followed up its open-weights Qwen2 large language models with specialized variations.

Image generation continued its rapid march forward with a new version of Google’s flagship text-to-image model.

While some observers argue that large language models can’t produce truly original output, new work prompted them to generate novel scientific research.

Literary works are challenging to translate. Their relative length, cultural nuances, idiomatic expressions...

Seemingly an innocuous form of expression, ASCII art opens a new vector for jailbreak attacks on large language models (LLMs), enabling them to generate outputs that their developers tuned them to avoid producing.

Researchers increasingly fine-tune models on synthetic data, but generated datasets may not be sufficiently diverse. New work used agentic workflows to produce diverse synthetic datasets.

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.