August 22–28: 9 frontier papers out of 2,031 read.
Papers rated as moving the field
How we choose“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.”
The authors, in the abstract
A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies
“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 22–28: 208 cleared, 9 frontier
199 papers