Bats Research
We are a machine learning research group at Brown University. We work on improving the processes by which humans teach and instruct computers.
United States of America
Pinned Repositories
alfred
A system for prompted weak supervision.
bonito
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
csp
Learning to compose soft prompts for compositional zero-shot learning.
labelmodels
Lightweight implementations of generative label models for weakly supervised machine learning
menghini-neurips23-code
Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.
nayak-aclfindings24-code
planetarium
Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL
taglets
wiser
Framework for weakly supervised deep sequence taggers, focused on named entity recognition
zsl-kg
Framework for zero-shot learning with knowledge graphs.
Bats Research's Repositories
BatsResearch/bonito
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
BatsResearch/zsl-kg
Framework for zero-shot learning with knowledge graphs.
BatsResearch/csp
Learning to compose soft prompts for compositional zero-shot learning.
BatsResearch/wiser
Framework for weakly supervised deep sequence taggers, focused on named entity recognition
BatsResearch/alfred
A system for prompted weak supervision.
BatsResearch/menghini-neurips23-code
Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.
BatsResearch/planetarium
Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL
BatsResearch/nayak-aclfindings24-code
BatsResearch/taglets
BatsResearch/labelmodels
Lightweight implementations of generative label models for weakly supervised machine learning
BatsResearch/safranchik-aaai20-code
BatsResearch/cross-lingual-detox
Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages"
BatsResearch/nplm
A weak supervision framework for (partial) labeling functions
BatsResearch/LexC-Gen
Generate synthetic labeled data for extremely low-resource languages using bilingual lexicons.
BatsResearch/efsl
Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
BatsResearch/ex2
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
BatsResearch/fudd
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
BatsResearch/nayak-tmlr22-code
BatsResearch/yu-aistats22-code
BatsResearch/amcl
Adversarial Multi Class Labeling
BatsResearch/piriyakulkij-mlsys22-code
BatsResearch/mazzetto-aistats21-code
BatsResearch/mazzetto-neurips22-code
BatsResearch/su-bigdata23-code
Code Repository for IEEE BigData 23 Paper "Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision"
BatsResearch/clipseg
This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".
BatsResearch/LexC-Gen-Data-Archive
Data Repository for LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
BatsResearch/mazzetto-arxiv23-code
An Adaptive Method for Weak Supervision with Drifting Data
BatsResearch/mazzetto-icml21-code