Schedule

Day 1: 15 August 2026

9:00 Welcome

9:10 Keynote talk: Vera Schmitt

9:40 Paper session: Interpretable Machine Learning

Part-based Quantitative Analysis for Heatmaps
Out-of-Distribution Detection using Counterfactual Distance
Semirings Meet Interpretability: A Quantitative Logic for Model Explanations
The Directed Prediction Change - Efficient and Trustworthy Fidelity Assessment for Local Feature Attribution Methods

10:40 Coffee break

11:00 Paper session: Explainable Sequential Decision Making

Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning
Toward Template-Free Explainability for Monte Carlo Tree Search
Assessing Automatic Concept Extraction for Reinforcement Learning Policies
Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents

12:00 Lunch break (lunch not provided by IJCAI)

13:00 Paper session: Human-Centered XAI

Hu-CEMNIST: A Benchmark Dataset of Human-Generated Counterfactual Explanations for MNIST
Acceptance and Perception of AI: The Roles of Model Confidence, Correctness, and Counterfactual Explanations Formats
Addressing the Selection Problem in Explainable AI
Beyond Output Confidence - A Mechanistic Interpretability Analysis of Sycophantic Vulnerability in Large Language Models

14:00 Coffee break

14:20 Paper session

Global Explanations for Multivariate Time Series Forecasting Models via K-Order Markov Approximations
The Failures of Marginal Influence-Based Attribution Methods for Global Time Series Explanations
CRISP - a Methodological Framework for Complexity-Guided Visual Hidden-Layer xAI
When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

15:20 Paper session

Improving Human Oversight of AI Systems With Expert Feedback Using Interactive, Contrastive Explanations
Do Neural Networks Attend to Expert-Recognized Morphological Characters? An XAI Case Study in Small-Data Zooplankton Classification
Towards an Argumentative Foundation for Evaluative AI
Counterfactual Explanations Under Concept Drift
On the Reliability of Post-Hoc Attributions Under Adversarial Training

16:20 End of day 1

9:00 Welcome

9:10 Keynote talk: TBA

9:40 Paper session: Interpretable Machine Learning

Why Textual Rule Explanations Drift: A Mechanism-Level Diagnosis of Stability Failures in RL
Does Target Class Matter? A Reproducibility Study of Plausible Counterfactual Explanations for Image Classification
From Decoding to Explanation: Selecting and Validating Brain Regions in Task-fMRI
Evaluating Explanation-Driven Vision–Language Reasoning via Generation Order Interventions

10:40 Coffee break

11:00 Paper session: Explainable Sequential Decision Making

CSTA++: Unifying State, Action Temporal Abstractions and Causal Information for Contrastive Policy Explanations
BXRL: Behavior-Explainable Reinforcement Learning
Forecasting-Conditioned Reinforcement Learning: Anticipatable Policies via Multi-Step Self-Forecasting
Sequential Decision-Making with Explanatory Actions

12:00 Lunch break (lunch not provided by IJCAI)

13:00 Paper session: Human-Centered XAI

Explaining Risk in High Stakes Domains
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders
Counterfactuals by Design: Residual Decomposition and Back-to-Normality Editing for Time Series
Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance

14:00 Coffee break

14:20 Paper session: Interpretable Machine Learning

Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation
Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation
Do Linear Probes Generalize Better in Persona Coordinates?
FlagGAM: Rule-Based Generalized Additive Modeling for Explainable Tabular Prediction
Brain–Model Alignment as a Probe for Subliminal Learning

15:40 Poster session

16:20 Fishbowl and closing

17:00 End of day 2

Page updated

Google Sites

Report abuse