Amos, Ido

3 publications

IJCAI 2025 Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors (Extended Abstract) Ido Amos, Jonathan Berant, Ankit Gupta

ICML 2024 Graph Neural Networks Use Graphs When They Shouldn’t Maya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach, Amir Globerson

ICLR 2024 Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors Ido Amos, Jonathan Berant, Ankit Gupta