AI Research Radar
February 23 – March 1: no frontier papers out of 284 read.
Frontier
Papers rated as moving the field
How we chooseNone of the 5 cleared papers this week was rated frontier.
The week by field
Feb 23 – Mar 1: 5 cleared, 0 frontier
The week’s papers have not been sorted into fields yet.
Models under test
Papers this week that name the model
Labs publishing
Papers this week with an author at the lab
Also cleared
5 papers
- Gaussian DP for Reporting Differential Privacy Guarantees in Machine LearningGoogle
- Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language ModelsCode
- AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI
- Text-Only Data Synthesis for Vision Language Model Training
- When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output