71 citations · 157 across the 7 of their papers we have counts for
8 papers
GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
Shivanshu Gupta, Clemens Rosenbaum, Ethan R. Elenberg
In-context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance c…
CEREAL: Few-Sample Clustering Evaluation
Nihal V. Nayak, Ethan R. Elenberg, Clemens Rosenbaum
Evaluating clustering quality with reliable evaluation metrics like normalized mutual information (NMI) requires labeled data that can be expensive to annotate. We focus on the und…
On the Role of Weight Sharing During Deep Option Learning
Matthew Riemer, Ignacio Cases, Clemens Rosenbaum +2
The options framework is a popular approach for building temporally extended actions in reinforcement learning. In particular, the option-critic architecture provides general purpo…
Routing Networks and the Challenges of Modular and Compositional Computation
Clemens Rosenbaum, Ignacio Cases, Matthew Riemer +1
Compositionality is a key strategy for addressing combinatorial complexity and the curse of dimensionality. Recent work has shown that compositional solutions can be learned and of…
Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning
Clemens Rosenbaum, Tim Klinger, Matthew Riemer
Multi-task learning (MTL) with neural networks leverages commonalities in tasks to improve performance, but often suffers from task interference which reduces the benefits of trans…
Eigenoption Discovery through the Deep Successor Representation
Marlos C. Machado, Clemens Rosenbaum, Xiaoxiao Guo +3
Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning. However, autonomously learn…