Europe
Enhancing Efficiency of Generated Code via Self-Optimization Dong Huang
These profiles are fed back to the LLM, which then revises the code to reduce overhead.
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity Zhanpeng Zhou 1, Yongyi Y ang 2, Xiaojiang Y ang 1, Junchi Y an
Furthermore, we delve deeper into the underlying factors contributing to LLFC, which reveal new insights into the permutation approaches.
FAST opic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model Xiaobao Wu1 Thong Nguyen
Topic models have been evolving rapidly over the years, from conventional to recent neural models.
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
Electrocardiogram (ECG) signals provide essential information about the heart's
Scaling MLPs: AT ale of Inductive Bias
Empirical insights into MLPs are important for multiple reasons.
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
Most of the literature in fair machine learning focuses on defining and achieving fairness criteria in the context of prediction, while not explicitly focusing on how these predictions may be used later on in the pipeline.
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Ideally, we would like methods that train LMs only once ( i.e., one-shot) with a fixed objective, as in