August 25–31: 9 frontier papers out of 2,028 read.
Papers rated as moving the field
How we choose“Results show that appropriate harness design can meaningfully improve performance, particularly on demanding workflows, while the effectiveness of specific designs can vary across foundation models.”
The authors, in the abstract
“Experiments show that current VLMs struggle with industrial assembly reasoning, often producing inaccurate poses, invalid mating relationships, part interpenetration, and degraded performance as assembly complexity increases.”
“EASEL-9B, trained on EASEL-Data, surpasses the base model by a relative 6.3%, ranking third among all evaluated models.”
“A broad "in any form" policy clause also closes it at the acting model (to 0%) but is brittle (dropping the catch-all reopens it to 48.8%).”
“Scores reached 87.6 and 94.9, but the highest Pass Rates were only 4% and 0%.”
“PII extraction rises sharply under both: on DeepSeek-V3.1, verbatim recall@k increases from 0.155 to 0.370, a 2.4x gain.”
“We show that this is a failure of composition rather than an implementation detail.”
Aug 25–31: 198 cleared, 9 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
189 papers