Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation
While there has been a surge of interest in automated scientific discovery (ASD), especially with the emergence of LLMs, it remains challenging for tools to generate hypotheses that are both…
LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape
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…
Context-Aware RL for Agentic and Multimodal LLMs
Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle…
Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension
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
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
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
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
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
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
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…