Profile

Yiran Huang is a a PhD student at the Explainable Machine Learning group and the International Max Planck Research School for Intelligent Systems (IMPRS-IS), supervised by Prof. Zeynep Akata and Prof. Wenjia Xu. She received her Master’s degree in Robotics, Cognition, Intelligence at Technical University of Munich in 2023 and Bachelor’s degree in Automotive Engineering at Tongji University in 2020. During summer 2021, she worked as a research intern Bosch Sensortec. Her research interest include vision & language, multi-modal learning as well as zero shot learning.

Publications

Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers.
Yiran Huang, Karsten Roth, Quentin Bouniot, Wenjia Xu, Zeynep Akata
ICML 2026 Spotlight
Paper

Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency.
Yiran Huang, Lukas Thede, Massimiliano Mancini, Wenjia Xu, Zeynep Akata
IJCV 2026
Paper | Code

Towards understanding multimodal in-context learning.
Yiran Huang, Karsten Roth, Quentin Bouniot, Wenjia Xu, Zeynep Akata
NeurIPS 2025 workshop What Can('t) Transformers Do?
Paper

Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs).
Leander Girrbach, Stephan Alaniz, Yiran Huang, Trevor Darrell and Zeynep Akata
ICLR 2025
Paper | Code

Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study.
Yiran Huang, Lukas Thede, Massimiliano Mancini, Wenjia Xu, Zeynep Akata
GCPR 2025
Paper | Code