5 papers
Cross-Entropy Guided Routing in Mixture-of-Experts Large Language Models
Yury Nahshan, Nati Daniel, Jacob Goldberger +1
Sparse mixture-of-experts (MoE) large language models scale model capacity by routing each token to a small subset of experts. Their routers are regularized with load balancing ter…
MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
Gilad Aviv, Jacob Goldberger, Yoli Shavit
We introduce Mixture-of-Gaussians with Uncertainty-based Gating (MoGU), a novel Mixture-of-Experts (MoE) framework designed for regression tasks. MoGU replaces standard learned gat…
Efficient Conformal Prediction for Regression Models under Label Noise
Yahav Cohen, Jacob Goldberger, Tom Tirer
In high-stakes scenarios, such as medical imaging applications, it is critical to equip the predictions of a regression model with reliable confidence intervals. Recently, Conforma…
Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
Yuval Grinberg, Nimrod Harel, Jacob Goldberger +1
Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global…
The Power of Summary-Source Alignments
Ori Ernst, Ori Shapira, Aviv Slobodkin +5
Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection, followed by text generation. In this context, alignment…