Together Open Deep Research

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.

Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to ex…

In-Context Learning User Simulators for Task-Oriented Dialog Systems

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

Conversational AI tooling & personas built on Cohere's LLMs

Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning, COLING 2022

[COLING22] An End-to-End Library for Evaluating Natural Language Generation

Code to reproduce LREC Paper Simplifying Semantic Annotations of SMCalFlow

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

Official Repository for EvalRS @ CIKM 2022: a Rounded Evaluation of Recommender Systems

A python package for benchmarking interpretability techniques on Transformers.

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

A python package to enrich Twitter Data

Behavioral "black-box" testing for recommender systems

A statistical measure of relative semantic polarization for pairs of textual corpora. EMNLP2021.

1passel is a very simple tool to integrate 1password into emacs.

CLIP (Contrastive Language–Image Pre-training) for Italian

Implementation and helper scripts for the BART-TL model - https://www.aclweb.org/anthology/2021.eacl-main.121/