Friday, June 19: 2 frontier papers out of 419 read.
Papers rated as moving the field
How we choose“In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2.”
The authors, in the abstract
Towards Highly Efficient Million-Token Context Intelligence
“Cross-architecture transfer via ridge regression maps yields large behavioral suppression (up to 46 points) but fails specificity controls as random and orthogonal directions perform comparably.”
Jun 13–19: 194 cleared, 18 frontier
The week’s papers have not been sorted into fields yet.
Papers this week that name the model
Papers this week with an author at the lab
31 papers