GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models Paper • 2411.05830 • Published Nov 5, 2024 • 20
Just Say the Name: Online Continual Learning with Category Names Only via Data Generation Paper • 2403.10853 • Published Mar 16, 2024
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order Paper • 2404.00399 • Published Mar 30, 2024 • 42
Challenging Common Assumptions about Catastrophic Forgetting Paper • 2207.04543 • Published Jul 10, 2022
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models Paper • 2206.04615 • Published Jun 9, 2022 • 5
Reprogramming under constraints: Revisiting efficient and reliable transferability of lottery tickets Paper • 2308.14969 • Published Aug 29, 2023
Mish: A Self Regularized Non-Monotonic Activation Function Paper • 1908.08681 • Published Aug 23, 2019 • 1