no code implementations • 6 Mar 2024 • Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar, Bryon Aragam, Victor Veitch
To that end, we introduce a simple latent variable model to abstract and formalize the concept dynamics of the next token prediction.
no code implementations • 8 Feb 2024 • Zhuokai Zhao, Yibo Jiang, Yuxin Chen
Active Learning (AL) has gained prominence in integrating data-intensive machine learning (ML) models into domains with limited labeled data.
no code implementations • 28 Sep 2023 • Chaoqi Wang, Yibo Jiang, Chenghao Yang, Han Liu, Yuxin Chen
The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.
1 code implementation • 4 Jul 2022 • Yibo Jiang, Victor Veitch
In this paper, we study representation learning under a particular notion of domain shift that both respects causal invariance and that naturally handles the "anti-causal" structure.
no code implementations • ICML 2020 • Yibo Jiang, Cengiz Pehlevan
Recent work showed that overparameterized autoencoders can be trained to implement associative memory via iterative maps, when the trained input-output Jacobian of the network has all of its eigenvalue norms strictly below one.
no code implementations • 30 Oct 2019 • Yibo Jiang, Nakul Verma
By providing multiple types of training datasets as inputs, our model has the ability to generalize well on unseen datasets (new clustering tasks).
no code implementations • 16 Oct 2019 • Daniel Jiwoong Im, Yibo Jiang, Nakul Verma
By leveraging this refined control, we demonstrate that there are multiple principled ways to update MAML and show that the classic MAML optimization is simply a special case of second-order Runge-Kutta method that mainly focuses on fast-adaptation.