2 papers
cs.CV2026
A Good Initialization is All You Need for Faithful Visual Attribution
Zihan Gu, Jiayu Wang, Hua Zhang +1
Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion faithfulness frontier by maski…
cs.LG2026
Deconstructing Positional Information: From Attention Logits to Training Biases
Zihan Gu, Ruoyu Chen, Han Zhang +2
Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and tran…