Stephen H. Bach

Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

2020 · arXiv (Cornell University)

In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose the problem of extended few-shot learning to study these scenarios. We …

TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data

2021 · arXiv (Cornell University)

Artifacts for the Artifact Evaluation of MLSys 2022 TAGLETS is a system that automatically and efficiently exploits all available data, including labeled, unlabeled, and auxiliary data, for a given task to produce a single, robust …

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning

2023 · arXiv (Cornell University)

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e., heuristic …

Multitask Prompted Training Enables Zero-Shot Task Generalization

2021 · arXiv (Cornell University)

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning …