385 citations · 1.1k across the 18 of their papers we have counts for
22 papers
Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models
Benjamin Hoover, Hendrik Strobelt, Dmitry Krotov +3
The generative process of Diffusion Models (DMs) has recently set state-of-the-art on many AI generation benchmarks. Though the generative process is traditionally understood as an…
Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion
Seongmin Lee, Benjamin Hoover, Hendrik Strobelt +7
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention. However, their complex structures and operations often pose challen…
The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference
Richard Brath, Daniel Keim, Johannes Knittel +3
With a constant increase of learned parameters, modern neural language models become increasingly more powerful. Yet, explaining these complex model's behavior remains a widely uns…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models
Hendrik Strobelt, Albert Webson, Victor Sanh +4
State-of-the-art neural language models can now be used to solve ad-hoc language tasks through zero-shot prompting without the need for supervised training. This approach has gaine…
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran +74
Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using…
GenNI: Human-AI Collaboration for Data-Backed Text Generation
Hendrik Strobelt, Jambay Kinley, Robert Krueger +3
Table2Text systems generate textual output based on structured data utilizing machine learning. These systems are essential for fluent natural language interfaces in tools such as…
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Sebastian Gehrmann, Tosin Adewumi, Karmanya Aggarwal +53
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of auto…
Understanding the Role of Individual Units in a Deep Neural Network
David Bau, Jun-Yan Zhu, Hendrik Strobelt +3
Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In thi…
Semantic Photo Manipulation with a Generative Image Prior
David Bau, Hendrik Strobelt, William Peebles +4
Despite the recent success of GANs in synthesizing images conditioned on inputs such as a user sketch, text, or semantic labels, manipulating the high-level attributes of an existi…
Seeing What a GAN Cannot Generate
David Bau, Jun-Yan Zhu, Jonas Wulff +4
Despite the success of Generative Adversarial Networks (GANs), mode collapse remains a serious issue during GAN training. To date, little work has focused on understanding and quan…
exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models
Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann
Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of lear…
ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion
Andreas Hinterreiter, Peter Ruch, Holger Stitz +4
Classifiers are among the most widely used supervised machine learning algorithms. Many classification models exist, and choosing the right one for a given task is difficult. Durin…
Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures
Dylan Cashman, Adam Perer, Remco Chang +1
Deep learning models require the configuration of many layers and parameters in order to get good results. However, there are currently few systematic guidelines for how to configu…
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Sebastian Gehrmann, Hendrik Strobelt, Robert Krüger +2
Automation of tasks can have critical consequences when humans lose agency over decision processes. Deep learning models are particularly susceptible since current black-box approa…
GLTR: Statistical Detection and Visualization of Generated Text
Sebastian Gehrmann, Hendrik Strobelt, Alexander M. Rush
The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generat…
NeuNetS: An Automated Synthesis Engine for Neural Network Design
Atin Sood, Benjamin Elder, Benjamin Herta +17
Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice. Pre-trained neural network models available through AP…
On the Units of GANs (Extended Abstract)
David Bau, Jun-Yan Zhu, Hendrik Strobelt +4
Generative Adversarial Networks (GANs) have achieved impressive results for many real-world applications. As an active research topic, many GAN variants have emerged with improveme…
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
David Bau, Jun-Yan Zhu, Hendrik Strobelt +4
Generative Adversarial Networks (GANs) have recently achieved impressive results for many real-world applications, and many GAN variants have emerged with improvements in sample qu…
Progressive Data Science: Potential and Challenges
Cagatay Turkay, Nicola Pezzotti, Carsten Binnig +7
Data science requires time-consuming iterative manual activities. In particular, activities such as data selection, preprocessing, transformation, and mining, highly depend on iter…
Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch +3
Neural Sequence-to-Sequence models have proven to be accurate and robust for many sequence prediction tasks, and have become the standard approach for automatic translation of text…
LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
Hendrik Strobelt, Sebastian Gehrmann, Hanspeter Pfister +1
Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden repre…