← Search

Zihan Gu

2 accepted papers

2026

Deconstructing Positional Information: From Attention Logits to Training Biases

ICLR 2026poster

Positional encodings, a mechanism for incorporating sequential information into the Transformer model, are central to contemporary research on neural architectures. Previous work has largely focused on understanding their function through the principle of distance attenuation, where proximity dictat…

Cited by 0SourceScholar
2026

PhaseWin Search Framework Enable Efficient Object-Level Interpretation

CVPR 2026

Attribution is essential for interpreting object-level foundation models. Recent methods based on submodular subset selection have achieved high faithfulness, but their efficiency limitations hinder practical deployment in real-world scenarios. To address this, we propose PhaseWin, a novel phase-win

Cited by 0SourcecodeScholar