output
20232026
most citedAI-AI Bias: large language models favor communications generated by large language models

22 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Thermodynamic Limits of Physical Intelligence

Koichi Takahashi, Yusuke Hayashi

Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption. To connect intelligence to physical efficiency, we propose two complementary bits-p…

cs.LG2024★ 1 cited

Backdoor defense, learnability and obfuscation

Paul Christiano, Jacob Hilton, Victor Lecomte +1

We introduce a formal notion of defendability against backdoors using a game between an attacker and a defender. In this game, the attacker modifies a function to behave differentl…