Education
A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of Θ(T2 / 3) and its Application to Best-of-Both-Worlds
Follow-the-Regularized-Leader (FTRL) is a powerful framework for various online learning problems. By designing its regularizer and learning rate to be adaptive to past observations, FTRL is known to work adaptively to various properties of an underlying environment.
CiteME: Can Language Models Accurately Cite Scientific Claims?
Thousands of new scientific papers are published each month.
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving Y uxuan Tong
In this work, we focus on mathematical problem-solving to explore enhancement of the mathematical reasoning abilities of pretrained LLMs. We investigate instruction tuning (Longpre et al., 2023; Wang
Understanding the Gains from Repeated Self-Distillation
Self-Distillation is a special type of knowledge distillation where the student model has the same architecture as the teacher model.
Make Continual Learning Stronger via C-Flat
How to balance the learning'sensitivity-stability' upon new task training and
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
To address these challenges, we propose boosting IR's performance by sharing the