Name: Bats Research
Type: Organization
Bio: We are a machine learning research group at Brown University. We work on improving the processes by which humans teach and instruct computers.
Location: United States of America
Blog: http://cs.brown.edu/people/sbach/
Bats Research's Projects
A system for prompted weak supervision.
Adversarial Multi Class Labeling
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".
Learning to compose soft prompts for compositional zero-shot learning.
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
Lightweight implementations of generative label models for weakly supervised machine learning
Generate synthetic labeled data for extremely low-resource languages using bilingual lexicons.
Data Repository for LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
An Adaptive Method for Weak Supervision with Drifting Data
Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.
A weak supervision framework for (partial) labeling functions
Code Repository for IEEE BigData 23 Paper "Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision"
Framework for weakly supervised deep sequence taggers, focused on named entity recognition
Framework for zero-shot learning with knowledge graphs.