"attention mechanism analysis" Papers
6 papers found
Attribution-Driven Adaptive Token Pruning for Transformers
YAOYAO YAN, Hui Yu, Weizhi Xu
NeurIPS 2025poster
Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
Xin Zou, Di Lu, Yizhou Wang et al.
NeurIPS 2025posterarXiv:2510.02912
7
citations
Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
Joonghyuk Shin, Alchan Hwang, Yujin Kim et al.
ICCV 2025posterarXiv:2508.07519
4
citations
One Head to Rule Them All: Amplifying LVLM Safety through a Single Critical Attention Head
Junhao Xia, Haotian Zhu, Shuchao Pang et al.
NeurIPS 2025poster
Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
Gouki Gouki, Hiroki Furuta, Yusuke Iwasawa et al.
ICLR 2025posterarXiv:2501.06254
9
citations
Why Larger Language Models Do In-context Learning Differently?
Zhenmei Shi, Junyi Wei, Zhuoyan Xu et al.
ICML 2024poster