Stephan Alaniz

Assistant Professor@Télécom Paris·法国·OpenReview

研究方向

interpretability · explainable AI · reinforcement learning · deep learning · computer vision · generative models · representation learning · large language models · multimodal learning

5.5

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models

ICLR 2026Poster

二作

4.0

When We Don’t See the Same Picture: Aligning Agents with Divergent Visual Spaces

ICLR 2026Rejected

二作

3.5

Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs

ICLR 2026Rejected

三作

2.7

A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models

ICLR 2026Withdrawn

二作

2.5

Towards Automatic Discovery and Explanation of Differences Between Vision Models

合作者 (19)

Stephan Alaniz

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models

When We Don’t See the Same Picture: Aligning Agents with Divergent Visual Spaces

Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs

A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models

Towards Automatic Discovery and Explanation of Differences Between Vision Models

Concept-Guided Interpretability via Neural Chunking

A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models

Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

Adapting Communicating MLLMs on the Fly in Referring Expression Tasks