AI Research Radar
July 29 – August 4: 1 frontier paper out of 520 read.
Frontier
Papers rated as moving the field
How we chooseThe week by field
Jul 29 – Aug 4: 8 cleared, 1 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
- IBM1
Also cleared
7 papers
- Dropping Just a Handful of Preferences Can Change Top Large Language Model RankingsIBM
- GroundAct: Can LLM Agents Ground Actions in Environmental States?
- Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
- VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
- The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
- LaQual: An Automated Framework for LLM App Quality Evaluation
- Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning