qbouniot.github.io·há 2 meses Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers
Yiran Huang, Karsten Roth, Quentin Bouniot, Wenjia Xu, Zeynep Akata
International Conference on Machine Learning (ICML), 2026
Transformer-based multimodal large language models often exhibit in-cont
