Nicholas Apostoloff

Principal Researcher@Apple·英国·OpenReview

研究方向

network introspection · responsible AI · fairness · deep learning · social signal processing · performance capture · alpha matting · image segmentation · natural image statistics · computer vision

7.5

Controlling Language and Diffusion Models by Transporting Activations

ICLR 2025Spotlight

6.5

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution

COLM 2025Poster

通讯

6.0

Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models

合作者 (20)

Nicholas Apostoloff

Controlling Language and Diffusion Models by Transporting Activations

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution

Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models

Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs

Uncovering Intersectional Stereotypes in Humans and Large Language Models

Advancing Differential Privacy through Synthetic Dataset Alignment