top of page


Visualizing transformer self attention and cross attention
At the heart of their success lies a powerful mechanism: transformer self attention and cross attention.
Bryan Downing
Jan 303 min read
16 views
0 comments


Chinese AI Startup DeepSeek abliteration from quant hedge fund
The rapid evolution of artificial intelligence has become a global race, with companies and research institutions worldwide vying to creat
Bryan Downing
Jan 253 min read
28 views
0 comments
bottom of page