activity
20242026
collaborators

5 papers

cs.AI2026

Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models

Katrina Brown, Aneesh Muppidi, Rana Shahout

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per q…

cs.CL2025

Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language Models

Sid Bharthulwar, John Rho, Katrina Brown

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt upd…

cs.CL2025

Order Independence With Finetuning

Katrina Brown, Reid McIlroy

Large language models (LLMs) demonstrate remarkable performance on many NLP tasks, yet often exhibit order dependence: simply reordering semantically identical tokens (e.g., answer…

cs.LG2024

Diverse Concept Proposals for Concept Bottleneck Models

Katrina Brown, Marton Havasi, Finale Doshi-Velez

Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number o…

cs.CL2024

Order-Independence Without Fine Tuning

Reid McIlroy-Young, Katrina Brown, Conlan Olson +2

The development of generative language models that can create long and coherent textual outputs via autoregression has lead to a proliferation of uses and a corresponding sweep of…