5 papers
Spectral Feedback for Test-Time Alignment of Protein Diffusion Models
Shai Dickman, Mert Cemri, Landon Butler +1
Reward maximization alignment methods for discrete diffusion models have primarily focused on steering the reverse process, either by influencing token logits or by selecting favor…
An Odd Estimator for Shapley Values
Fabian Fumagalli, Landon Butler, Justin Singh Kang +2
The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference. However, its exact computati…
ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
Landon Butler, Abhineet Agarwal, Justin Singh Kang +3
Large Language Models (LLMs) have achieved remarkable performance by capturing complex interactions between input features. To identify these interactions, most existing approaches…
SPEX: Scaling Feature Interaction Explanations for LLMs
Justin Singh Kang, Landon Butler, Abhineet Agarwal +4
Large language models (LLMs) have revolutionized machine learning due to their ability to capture complex interactions between input features. Popular post-hoc explanation methods…
Learning to Understand: Identifying Interactions via the Möbius Transform
Justin S. Kang, Yigit E. Erginbas, Landon Butler +2
One of the key challenges in machine learning is to find interpretable representations of learned functions. The Möbius transform is essential for this purpose, as its coefficients…