Picture for Ido Hakimi

Ido Hakimi

Department of Computer Science, Technion

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

Add code
Oct 10, 2024
Viaarxiv icon

q2d: Turning Questions into Dialogs to Teach Models How to Search

Add code
Apr 27, 2023
Viaarxiv icon

Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays

Add code
Jun 23, 2021
Figure 1 for Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays
Figure 2 for Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays
Viaarxiv icon

Gap Aware Mitigation of Gradient Staleness

Add code
Sep 25, 2019
Figure 1 for Gap Aware Mitigation of Gradient Staleness
Figure 2 for Gap Aware Mitigation of Gradient Staleness
Figure 3 for Gap Aware Mitigation of Gradient Staleness
Figure 4 for Gap Aware Mitigation of Gradient Staleness
Viaarxiv icon

Taming Momentum in a Distributed Asynchronous Environment

Add code
Jul 26, 2019
Figure 1 for Taming Momentum in a Distributed Asynchronous Environment
Figure 2 for Taming Momentum in a Distributed Asynchronous Environment
Figure 3 for Taming Momentum in a Distributed Asynchronous Environment
Figure 4 for Taming Momentum in a Distributed Asynchronous Environment
Viaarxiv icon