VIS Short Papers: Is the Model Even Thinking?

Session chair:Yong Wang

Room:America South

Time:Thursday, Nov 12 @ 08:00 - 09:30 (US/Eastern)

Presentations in this session

08:00 - 08:11

Evaluating a Visual Query Tracer and Builder for Learning Declarative Logic Programming

Authors: Julián Méndez, Lukas Gerlach, Tobias Wieland, Alex Ivliev, Markus Krötzsch, Raimund Dachselt

08:11 - 08:22

Attention Dynamics in Diffusion Models: A Visual Analytics Framework for HumanÐAI Collaboration

Authors: Yiran Xiao, George Legrady

08:22 - 08:33

VEIL: How Visual Encoding Hijacking Induces Bias In Vision Models

Authors: Suranjana Sooraj, Xuyang Chen, Madhumitha Venkatesan, Dongyu Liu

08:33 - 08:44

Exploring Text Classification Models with Sparse Autoencoders

Authors: Daniel Kerrigan, Brian Barr, Enrico Bertini

08:44 - 08:55

UNIPO: Unified Interactive Visual Explanation for RL Fine-Tuning Policy Optimization

Authors: Aeree Cho, Alexander D Greenhalgh, Jonathan Bodea, ShengYun Peng, Duen Horng Chau

08:55 - 09:06

MLLM Perception of Color-Encoded Scalar Fields Reveals Model-Dependent Inversion of Chain-of-Thought

Authors: Minyi Liu, Yue Zhao, Xiaoyang Song, Shufan Qian, Yulong Bian, Qiong Zeng

09:06 - 09:17

AttentionRadViz: Token-Anchored Attention Profile Visualization for Transformer Head Analysis

Authors: Jared Wilber

09:17 - 09:28

Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs

Authors: Maeve Hutchinson, Abderrahmane Wassim Mehdaoui, Pranava Madhyastha