Ghazal Hosseini Mighan

According to our database, Ghazal Hosseini Mighan authored at least 3 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation.

Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr

Trans. Mach. Learn. Res., 2026

2025

Large (Vision) Language Models are Unsupervised In-Context Learners.

Artyom Gadetsky, Andrei Atanov, Yulun Jiang, Zhitong Gao, Ghazal Hosseini Mighan, Amir Zamir, Maria Brbic

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding.

Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr

CoRR, 2024