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

5 papers

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…

gr-qc2025

Emergent Universe Scenario in the Modified Chaplygin gas : Towards an Exact Solution and Observational Constraints

D. Panigrahi, S. Chatterjee, B. C. Paul

The Modified Chaplygin Gas (MCG) model is revisited as a unified framework for describing cosmic evolution. Due to the nonlinear field equations, exact solutions in cosmic time are…

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…

cs.CL2024★ 22 cited

AI-AI Bias: large language models favor communications generated by large language models

Walter Laurito, Benjamin Davis, Peli Grietzer +3

Are large language models (LLMs) biased in favor of communications produced by LLMs, leading to possible antihuman discrimination? Using a classical experimental design inspired by…

q-bio.QM2023★ 11 cited

The Protein Engineering Tournament: An Open Science Benchmark for Protein Modeling and Design

Chase Armer, Hassan Kane, Dana Cortade +7

The grand challenge of protein engineering is the development of computational models that can characterize and generate protein sequences for any arbitrary function. However, prog…