Search Results for author:
Found 7 papers, 1 papers with code
On the Origins of Linear Representations in Large Language Models
To that end, we introduce a simple latent variable model to abstract and formalize the concept dynamics of the next token prediction.
Direct Acquisition Optimization for Low-Budget Active Learning
Active Learning (AL) has gained prominence in integrating data-intensive machine learning (ML) models into domains with limited labeled data.
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
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.
Invariant and Transportable Representations for Anti-Causal Domain Shifts
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.
Associative Memory in Iterated Overparameterized Sigmoid Autoencoders
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.
Meta-Learning to Cluster
By providing multiple types of training datasets as inputs, our model has the ability to generalize well on unseen datasets (new clustering tasks).
Model-Agnostic Meta-Learning using Runge-Kutta Methods
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.
