1 code implementation • 6 Jun 2024 • Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, Dan Hendrycks
Existing techniques aimed at improving alignment, such as refusal training, are often bypassed.
no code implementations • 30 May 2024 • Dylan Zhang, Justin Wang, Francois Charton
Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world.
no code implementations • 16 Feb 2024 • Dylan Zhang, Justin Wang, Francois Charton
We investigate the trade-off between the number of instructions the model is trained on and the number of training samples provided for each instruction and observe that the diversity of the instruction set determines generalization.
no code implementations • 24 Jun 2020 • Justin Wang, Edward Xu, Kangrui Xue, Lukasz Kidzinski
In this work, we build upon existing methods for occlusion-aware 3D pose detection in videos.