![[Paper Review] Qwen 3 Technical Report](https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen3.png){kind=logo}
[Paper Review] Qwen 3 Technical Report
Qwen 3: The Evolution of a Giant MoE Language Model with Adjustable Reasoning Depth TL;DR (in one line) Qwen 3 couples a user-controllable Thinking Budget with a…
Posts
All posts on technology, daily life, and thoughts.
118 pages
18 /
20
K-Beauty: Beyond 'Accidental Success' to 'Structural Growth'
In a previous post, "Is K-Beauty at a Crossroads for a New Leap?," I discussed the paradigm shift and new opportunities facing K-Beauty. We looked at how the convergence…
A Guide to Migrating from Jekyll to Hugo
A Guide to Migrating from Jekyll to Hugo When I decided to migrate from Jekyll to Hugo, I consulted numerous documents and tutorials but still encountered quite a few…
K-Beauty: On the Verge of a New Leap Forward?
K-Beauty: Poised for a New Leap Forward The K-beauty industry has recently been capturing the spotlight once again. As an investor looking into the sector, I feel that…
Migrating My Blog from Jekyll to Hugo
Why I Migrated My Blog from Jekyll to Hugo When I first started blogging back in 2021, I chose Jekyll because it was officially supported by GitHub Pages and had abundant…
![[Paper Review] Massive Activations in Large Language Models](https://eric-mingjie.github.io/massive-activations/assets/main_teaser_final.png)
[Paper Review] Massive Activations in Large Language Models
Massive Activations, Hidden Biases: A Reinterpretation of Self-Attention’s Secrets TL;DR Just 4–10 extreme scalar values (×10,000) out of tens of millions can…