Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists
Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text. While blind or low-vision (BLV) scientists have traditionally relied on…
Narrative Scaffolding: A Narrative-First Framework for Data-Driven Sensemaking
When exploring data, analysts construct narratives about what the data means by asking questions, generating visualizations, reflecting on patterns, and revising their interpretations as new…
Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users
Deep Research (DR) systems help researchers cope with ballooning publishing counts. Such tools synthesize scientific papers to answer research queries, but lack understanding of their users. We…
Disentangling the effects of sea surface temperature and CO$_2$ in global machine learned weather-climate emulators
While previous versions of the Ai2 Climate Emulator (ACE) have been trained with CO$_2$ as a forcing, they are only accurate within a narrow range of scenarios, for example climate over the last 80…
VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding.…
SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators
Traditional numerical global climate models simulate the full Earth system by exchanging boundary conditions between separate simulators of the atmosphere, ocean, sea ice, land surface, and other…
Scientific reasoning does not reliably translate into scientific forecasting in frontier AI
AI systems are increasingly used to support forward-looking scientific judgment, but it remains unclear whether they can form reliable expectations about future scientific advances. Here we show…
AIMIP Phase 1: systematic evaluations of AI weather and climate models
We present the AI weather and climate model intercomparison project (AIMIP), phase 1. Drawing from the rich tradition of intercomparisons in climate model development, we specify a common…
Improving Attributed Long-form Question Answering with Intent Awareness
Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they…
Cocoa: Co-Planning and Co-Execution with AI Agents
As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent…