Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
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…
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…
From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models
While Large Language Models have improved rapidly, many fundamental questions remain about how to evaluate the knowledge and reasoning abilities they acquire, and how such evaluations relate to the…
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…
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…
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.g., to ask clarification questions, prompt for…
Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
Recent work describes what transformers can and cannot compute through connections to boolean circuits, but existing results lack exact characterizations and are sensitive to modeling choices.…
Why Are Linear RNNs More Parallelizable?
The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressivity benefits of…
Language Models as Higher-Order Planning Formalizers
Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems become more complex. LLM-as-Formalizers aim to…