Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape

Hita KambhamettuBhavana Dalvi MishraAndrew HeadPao Siangliulue
2026
UIST 2026

Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively reviewing literature and refining an… 

Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension

Amanda BertschLuca SoldainiMatthew R. GormleyD. Groeneveld
2026
COLM

One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case in the long context… 

Olmo Hybrid: From Theory to Practice and Back

William MerrillYanhong LiTyler RomeroAshish Sabharwal
2026
COLM

Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention. Yet there is no… 

Measuring AI Scientists: From Exams to Discovery

Yuanqi DuSteven DillmannJon LaurentChenru Duan
2026
arXiv

Large language models and agentic systems are increasingly embedded across the scientific work-flow, from literature synthesis and hypothesis generation to code execution, data analysis and writing.… 

Process-Oriented Evaluation of AI-Assisted Scientific Writing

Patrick Queiroz Da SilvaSanchaita HazraDoeun LeeBodhisattwa Prasad Majumder
2026
Conference on Language Modeling

Bad writing hinders the publication of science. The role of artificial intelligence (AI) in generating and editing scientific texts remains unsettled. Abstracts serve as the critical gateway to… 

Stochastic Emulation of a Fully Coupled Preindustrial E3SMv3 Simulation

E. WuJames P. C. DuncanTroy ArcomanoPeter M. Caldwell
2026
arXiv

We present a stochastic coupled emulator of E3SM version 3, built on the SamudrACE framework, which couples an atmosphere emulator (ACE2) with a full-depth ocean emulator (Samudra). We replace the… 

ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery

Haofei YuJiaxuan YouPeter ClarkKyle Richardson
2026
COLM 2026

Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have access to a large number of artifacts. Yet, a… 

CoTs as Tractable Probabilistic Programs

Kyle RichardsonYu FengPoorva GargDan Roth
2026
9th Workshop on Tractable Probabilistic Modeling (TPM@UAI)

Chain-of-thought (CoT) traces are used across language model prompting, training, test-time inference, and interpretability, yet they are often modeled in task-specific ways. We propose treating CoT… 

Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists

Arnavi Chheda-KotharyLucy Lu WangJoseph Chee ChangJonathan Bragg
2026
ASSETS

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

Oliver HuangMuhammad FatirTian LuoCarolina Nobre
2026
International Conference on Intelligent User Interfaces (IUI)

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… 

1-10Next