VISxAI: 9th Workshop on Visualization for AI Explainability


Session chair:TBA

Room:America south

Time:Monday, Nov 9 @ 13:00 - 16:30 (US/Eastern)

Organizers:Alex Bäuerle,Angie Boggust,Catherine Yeh,Fred Hohman

Website:https://visxai.io/

The VISxAI workshop, throughout its past eight iterations, has been a platform for knowledge exchange between researchers with different backgrounds interested in explaining machine learning models through visualization. Its focus on explainables submissions that visually and interactively explain machine learning concepts ranges in complexity from clustering methods to algorithmic biases. These explainables have served as educational resources that have had an impact beyond the academic community. The workshop also always hosted great keynote speakers that connected the domains of visualization and state-of-the-art machine learning and explored the impact visualization can have on explainability. Following the success of VISxAI’25, our goal for this upcoming iteration of VISxAI is to combine strong interactive explainables and great presentations with the interactivity of breakout sessions and live demos. Participants will be encouraged to exchange ideas about the future of visual explainability, interactive articles, and explorable explanations. Furthermore, we will provide a platform for new visualization and interaction ideas that explain machine learning models.

Papers

arxAIv: An AI Generated Research Universe

Authors: Allison Andreyev

Byte-Pair Encoding Explainer: An Interactive Visualization for Understanding Subword Tokenization

Authors: Philip Müller, Peter Steinbach

Embodied XAI Is All You Need: Tracing hierarchical VLM–PPO decisions via 4D spatio-temporal saliency

Authors: Suzan Mohammad Halim

Exploring The Geographic Assumptions in Text-to-Image Models with Underspecified Prompts

Authors: Giray Unlu, Amal Alnouri, Ahmed Mansour, Andreas Hinterreiter, Marc Streit

How to Win the Lottery within Neural Networks

Authors: Ammar Mustafa Nagri

Interpreting Bio-Foundation Models with Sparse Autoencoders

Authors: Jared Wilber, Tyler Carter Shimko

MoEXViz: Interactive Visualizations of Sparse Mixture-of-Experts

Authors: Chinmayee Raman, Hazim Hasan Bajamal, Reza Rawassizadeh

More Features Than Neurons

Authors: Nikhil Maturi

NCDL Explainer: Non-Cartesian Deep Learning Explained

Authors: Mohammad Sakib Hossain, Usman Alim

New Francisco or San York? A Visual Explanation of Text Diffusion

Authors: Susie S.Y. Li, Mingwei S.G. Li, Remco Chang

Rectified Flow Explainer: A Visual Introduction to Rectified Flows

Authors: Alec Helbling

Some Vector Algebra for Model Steering

Authors: Mingwei S.G. Li, Susie S.Y. Li, Remco Chang

Superposition Explainer: Visualizing Feature Overcompression Through Guided Experimentation

Authors: Philip Müller, Peter Steinbach

The Confident Machine

Authors: Shashank Bangalore Lakshman, Shravan Joshi

The Story of Inference-Time Scaling and the training-time loop behind it

Authors: Shashank Bangalore Lakshman, Scott Eiers

TokenTour: Tracing LLM Conversations from Messages to Tokens and KV Cache

Authors: Liwen Fan, Yu Zhang, Yuheng Zhao, Siming Chen

Visualizing and Comparing Distributions of Language Model Generations: interactive article

Authors: Emily Reif, Claire Y Yang, Jared Hwang, Deniz Nazar, Noah Smith, Jeffrey Heer