1 code implementation • 16 Jan 2024 • Xingjian Bai, Luke Melas-Kyriazi
We introduce the Fixed Point Diffusion Model (FPDM), a novel approach to image generation that integrates the concept of fixed point solving into the framework of diffusion-based generative modeling.
1 code implementation • NeurIPS 2023 • Xingjian Bai, Christian Coester
We explore the fundamental problem of sorting through the lens of learning-augmented algorithms, where algorithms can leverage possibly erroneous predictions to improve their efficiency.
no code implementations • 13 Oct 2023 • Jacek Karwowski, Oliver Hayman, Xingjian Bai, Klaus Kiendlhofer, Charlie Griffin, Joar Skalse
First, we propose a way to quantify the magnitude of this effect and show empirically that optimising an imperfect proxy reward often leads to the behaviour predicted by Goodhart's law for a wide range of environments and reward functions.
1 code implementation • NeurIPS 2023 • Xingjian Bai, Guangyi He, Yifan Jiang, Jan Obloj
To evaluate the distributional robustness of neural networks, we propose a first-order AA algorithm and its multi-step version.
no code implementations • ACL (WOAH) 2021 • Hannah Rose Kirk, Yennie Jun, Paulius Rauba, Gal Wachtel, Ruining Li, Xingjian Bai, Noah Broestl, Martin Doff-Sotta, Aleksandar Shtedritski, Yuki M. Asano
In this paper, we collect hateful and non-hateful memes from Pinterest to evaluate out-of-sample performance on models pre-trained on the Facebook dataset.