Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Application of the AI2 Climate Emulator to E3SMv2's global atmosphere model, with a focus on precipitation fidelity
Can the current successes of global machine learning-based weather simulators be generalized beyond 2-week forecasts to stable and accurate multiyear runs? The recently developed AI2 Climate…
OLMoE: Open Mixture-of-Experts Language Models
We introduce OLMoE, a fully open, state-of-the-art language model leveraging sparse Mixture-of-Experts (MoE). OLMoE-1B-7B has 7 billion (B) parameters but uses only 1B per input token. We pretrain…
Pushing the frontiers in climate modelling and analysis with machine learning
Climate modelling and analysis are facing new demands to enhance projections and climate information. Here we argue that now is the time to push the frontiers of machine learning beyond…
Weather and climate predicted accurately — without using a supercomputer
A cutting-edge global model of the atmosphere combines machine learning with a numerical model based on the laws of physics. This ‘hybrid’ system accurately predicts the weather — and even shows…
AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
Autonomous agents that address day-to-day digital tasks (e.g., ordering groceries for a household), must not only operate multiple apps (e.g., notes, messaging, shopping app) via APIs, but also…
Can Language Models Serve as Text-Based World Simulators?
Virtual environments play a key role in benchmarking advances in complex planning and decision-making tasks but are expensive and complicated to build by hand. Can current language models themselves…
Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning
We consider the task of building a dialogue system that can motivate users to adopt positive lifestyle changes: Motivational Interviewing. Addressing such a task requires a system that can infer…
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has…
Data Contamination Report from the 2024 CONDA Shared Task
The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where…
Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions
Multiple-choice question answering (MCQA) is a key competence of performant transformer language models that is tested by mainstream benchmarks. However, recent evidence shows that models can have…