Europe
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
To this end, two broad strategies have been outlined in prior literature to explain models.
6fdf57c71bc1f1ee29014b8dc52e723f-Paper-Conference.pdf
First, counterintuitively, we observe that pretrain-ing on more data shows no significant improvement in the model's capability to
Scaling Laws in Linear Regression: Compute, Parameters, and Data
From the perspective of statistical learning theory, (1) is rather intriguing. Moreover, they do not provide instance-wise matching lower bounds to verify the tightness of the upper bounds.
Localizing Memorization in SSL Vision Encoders Wenhao Wang
Memorization happens through the entire SSL encoder .
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
Given the description of an environment and a task, we use an LLM guided by the GIF-MCTS method to iteratively generate and refine a candidate CWM. The candidate's correctness is evaluated by checking if it correctly