Research Focus: Week of January 22, 2024
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Join Microsoft Research Forum (opens in new tab)…
Fifty Shades of Bias
This repo contains data and code for EMNLP’23 paper “Fifty Shades of Bias”: Normative Ratings of Gender Bias in GPT Generated English Text
Skeleton-of-Thought (SoT)
This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-the-art LLMs.…
SatCLIP
SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery [PyTorch implementation, dataset and pretrained models for the paper “SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery”]
PwR Studio
PwR Studio converts natural language (NL) instructions into robust code. Programming with Representations (PwR, pronounced “power”) is a software development approach that relies on a domain-specific language (DSL), or representation, defined by a developer specializing in…
The Prompt with Trevor Noah | Episode 4: How can large language models help people combat addiction?
What if you could have a friendly chat with an AI coach that knows how to help you quit smoking? That’s the idea behind Dr. Jonathan Bricker’s research, which uses large language models to create…