A multimodal large language model (MLLM) agent can receive instructions, capture images,
retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming …

How does the internal computation of a machine learning model transform inputs into
predictions? In this paper, we introduce a task called component modeling that aims to …

The goal of data attribution for text-to-image models is to identify the training images that
most influence the generation of a new image. Influence is defined such that, for a given …

Diffusion models (DMs) produce very detailed and high-quality images. Their power results
from extensive training on large amounts of data-usually scraped from the internet without …

Many training data attribution (TDA) methods aim to estimate how a model's behavior would
change if one or more data points were removed from the training set. Methods based on …

Generative artificial intelligence (AI) systems are trained on large data corpora to generate
new pieces of text, images, videos, and other media. There is growing concern that such …

Text-to-image diffusion models have made significant progress in generating naturalistic
images from textual inputs, and demonstrate the capacity to learn and represent complex …

While Explainable AI (XAI) aims to make AI understandable and useful to humans, it has
been criticised for relying too much on formalism and solutionism, focusing more on …

Deep generative models have demonstrated impressive performance in various computer
vision applications, including image synthesis, video generation, and medical analysis …

How can we attribute the behaviors of machine learning models to their training data? While
the classic influence function sheds light on the impact of individual samples, it often fails to …