Search Results for author:
Found 45 papers, 23 papers with code
GPT-2 Through the Lens of Vector Symbolic Architectures
Understanding the general priniciples behind transformer models remains a complex endeavor.
Dense Associative Memory Through the Lens of Random Features
Dense Associative Memories are high storage capacity variants of the Hopfield networks that are capable of storing a large number of memory patterns in the weights of the network of a given size.
Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities
Our work investigates how the integration of information from image and text modalities influences the performance and behavior of VLMs in visual question answering (VQA) and reasoning tasks.
Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to generalize to new data.
Interactive Analysis of LLMs using Meaningful Counterfactuals
First, the generated textual counterfactuals should be meaningful and readable to users and thus can be mentally compared to draw conclusions.
Interactive Visual Learning for Stable Diffusion
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention.
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision.
Multi-Level Explanations for Generative Language Models
To address the challenges of text as output and long text inputs, we propose a general framework called MExGen that can be instantiated with different attribution algorithms.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
Unraveling the Temporal Dynamics of the Unet in Diffusion Models
We propose an analytical method to systematically assess the impact of time steps and core Unet components on the final output.
RELIC: Investigating Large Language Model Responses using Self-Consistency
To address this challenge, we propose an interactive system that helps users gain insight into the reliability of the generated text.
Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models
The generative process of Diffusion Models (DMs) has recently set state-of-the-art on many AI generation benchmarks.
Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion
Diffusion Explainer tightly integrates a visual overview of Stable Diffusion's complex structure with explanations of the underlying operations.
Energy Transformer
Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory.
The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference
We motivate the use of visualization in relation to target users and common NLP pipelines.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models
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.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
Moreover, with saliency cards, we are able to analyze the research landscape in a more structured fashion to identify opportunities for new methods and evaluation metrics for unmet user needs.
LMdiff: A Visual Diff Tool to Compare Language Models
While different language models are ubiquitous in NLP, it is hard to contrast their outputs and identify which contexts one can handle better than the other.
GenNI: Human-AI Collaboration for Data-Backed Text Generation
These controls allow users to globally constrain model generations, without sacrificing the representation power of the deep learning models.
Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior
Saliency methods -- techniques to identify the importance of input features on a model's output -- are a common step in understanding neural network behavior.
FairyTailor: A Multimodal Generative Framework for Storytelling
Natural language generation (NLG) for storytelling is especially challenging because it requires the generated text to follow an overall theme while remaining creative and diverse to engage the reader.
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics.
Ranked #1 on
Extreme Summarization
on GEM-XSum
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+5
Latent Compass: Creation by Navigation
Our approach puts creators in the discovery loop during real-time tool use, in order to identify directions that are perceptually meaningful to them, and generate interpretable image translations along those directions.
Understanding the Role of Individual Units in a Deep Neural Network
Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes.
exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models
Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism.
Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
De novo therapeutic design is challenged by a vast chemical repertoire and multiple constraints, e. g., high broad-spectrum potency and low toxicity.
Semantic Photo Manipulation with a Generative Image Prior
First, it is hard for GANs to precisely reproduce an input image.
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
CogMol also includes insilico screening for assessing toxicity of parent molecules and their metabolites with a multi-task toxicity classifier, synthetic feasibility with a chemical retrosynthesis predictor, and target structure binding with docking simulations.
Seeing What a GAN Cannot Generate
Differences in statistics reveal object classes that are omitted by a GAN.
exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models
We present exBERT, an interactive tool named after the popular BERT language model, that provides insights into the meaning of the contextual representations by matching a human-specified input to similar contexts in a large annotated dataset.
ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion
The confusion matrix is an established way for visualizing these class errors, but it was not designed with temporal or comparative analysis in mind.
Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures
In this paper, we present Rapid Exploration of Model Architectures and Parameters, or REMAP, a visual analytics tool that allows a model builder to discover a deep learning model quickly via exploration and rapid experimentation of neural network architectures.
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Automation of tasks can have critical consequences when humans lose agency over decision processes.
GLTR: Statistical Detection and Visualization of Generated Text
The rapid improvement of language models has raised the specter of abuse of text generation systems.
Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection
We present the pipeline in an interactive visual tool to enable the exploration of the metrics, analysis of the learned latent space, and selection of the best model for a given task.
Visualizing and Understanding GANs
We present an analytic framework to visualize and understand GANs at the unit-, object-, and scene-level.
On the Units of GANs (Extended Abstract)
We quantify the causal effect of interpretable units by measuring the ability of interventions to control objects in the output.
NeuNetS: An Automated Synthesis Engine for Neural Network Design
Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice.
Progressive Data Science: Potential and Challenges
We discuss these challenges and outline first steps towards progressiveness, which, we argue, will ultimately help to significantly speed-up the overall data science process.
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
Then, we quantify the causal effect of interpretable units by measuring the ability of interventions to control objects in the output.
Debugging Sequence-to-Sequence Models with Seq2Seq-Vis
Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks.
Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
In this work, we present a visual analysis tool that allows interaction with a trained sequence-to-sequence model through each stage of the translation process.
LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics.
