9 papers
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
Xuan Zhao, Lena Krieger, Zhuo Cao +3
Counterfactual explanations (CFs) help understand machine learning models by identifying minimal input changes that would lead to alternative model outcomes. Recent work demonstrat…
Residual-Space Evolutionary Optimization via Flow-based Generative Models
Zhuo Cao, Lena Krieger, Fernanda Nader +3
Data editing with generative methods typically requires differentiable objectives and gradient-based search. However, these assumptions break down in flow-based settings, where edi…
Counterfactual Transport Flows for Offline Conservative Trajectory Refinement
Lena Krieger, Xuan Zhao, Zhuo Cao +3
Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback. A key diffi…
Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offs
Alessio Quercia, Arya Bangun, Ira Assent +1
Low-Rank Adaptation (LoRA) methods have emerged as crucial techniques for adapting large pre-trained models to downstream tasks under computational and memory constraints. However,…
Classifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes
Xuan Zhao, Zhuo Cao, Arya Bangun +2
Counterfactual explanations provide actionable insights by identifying minimal input changes required to achieve a desired model prediction. Beyond their interpretability benefits,…
LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
Zhuo Cao, Xuan Zhao, Lena Krieger +2
The growing integration of machine learning (ML) and artificial intelligence (AI) models into high-stakes domains such as healthcare and scientific research calls for models that a…