5 papers · 1 filter
Pretrained Persona Mixture Models and Tandem Models for Human Simulation
Minwoo Kang, Téa Wright, Seun Eisape +6
We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas, is inaccurate and produces st…
Learning to Refer from Estimated Listener Gaze
Téa Wright, Alane Suhr
We propose to finetune vision-language models to generate more pragmatically optimal referring expressions by transforming observations of incremental listener comprehension, in th…
An Investigation of Translationese in the Generations of Multilingual Large Language Models
Maria Valentini, Téa Wright, Julisa Granados +2
Text which has been translated from another language tends to carry with it evidence of translation$\unicode{x2014}$hence, it is often referred to as . Mul…
SATFormer: Learning When to Use Early Value Residuals in Transformers
Skye Gunasekaran, Téa Wright, Rui-Jie Zhu +1
Recent Transformer architectures expose later layers to representations computed in earlier layers, motivated by the observation that low-level features can become harder to recove…
ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text
Anya Ji, George Ma, Téa Wright +4
Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often stru…