Kathleen McKeown

PoSh: Using Scene Graphs to Guide LLMs-as-a-Judge for Detailed Image Descriptions

LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated News

Rethinking reasoning with Masked Diffusion Models

Guiding LLM Decision-Making with Fairness Reward Models

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

A General Framework for Inference-time Scaling and Steering of Diffusion Models

DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning