Massive-activations-VLMs. [ACL 2026] Code for paper: What Drives Attention Sinks? A Study of Massive Activations and Rotational Positional Encoding in Large Vision-Language Models

github.com/zhangbaijin/Massive-activations-VLMs

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.