Monday, April 27: 2 frontier papers out of 136 read.
Papers rated as moving the field
How we choose“We find that training with weak supervision can reliably elicit sandbagging models when supervised fine-tuning (SFT) and reinforcement learning (RL) are combined: SFT on weak demonstrations breaks the sandbagging behavior, enabling RL to then fully elicit performance.”
The authors, in the abstract
“Experiments on six representative VLA models show that RedVLA uncovers diverse unsafe behaviors and achieves the ASR up to 95.5% within 10 optimization iterations.”
Apr 21–27: 33 cleared, 3 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
10 papers