Bats Research

bonito

A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.

zsl-kg

Framework for zero-shot learning with knowledge graphs.

csp

Learning to compose soft prompts for compositional zero-shot learning.

wiser

Framework for weakly supervised deep sequence taggers, focused on named entity recognition

alfred

A system for prompted weak supervision.

menghini-neurips23-code

Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.

taglets

nayak-aclfindings24-code

planetarium

Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL

safranchik-aaai20-code

cross-lingual-detox

Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages"

labelmodels

Lightweight implementations of generative label models for weakly supervised machine learning

nplm

A weak supervision framework for (partial) labeling functions

efsl

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

ex2

If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions

LexC-Gen

Generate synthetic labeled data for extremely low-resource languages using bilingual lexicons.

fudd

Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

nayak-tmlr22-code

yu-aistats22-code

amcl

Adversarial Multi Class Labeling

piriyakulkij-mlsys22-code

mazzetto-aistats21-code

mazzetto-neurips22-code

su-bigdata23-code

Code Repository for IEEE BigData 23 Paper "Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision"

clipseg

This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

LexC-Gen-Data-Archive

Data Repository for LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons

mazzetto-arxiv23-code

An Adaptive Method for Weak Supervision with Drifting Data

mazzetto-icml21-code