activity
20192025
most citedTeacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

20 citations · 46 across the 8 of their papers we have counts for

collaborators

12 papers

cs.LG2025

Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?

Grgur Kovač, Jérémy Perez, Rémy Portelas +2

Large language models (LLMs) are increasingly used in the creation of online content, creating feedback loops as subsequent generations of models will be trained on this synthetic…

cs.CL2024★ 7 cited

Stick to your Role! Stability of Personal Values Expressed in Large Language Models

Grgur Kovač, Rémy Portelas, Masataka Sawayama +2

The standard way to study Large Language Models (LLMs) with benchmarks or psychology questionnaires is to provide many different queries from similar minimal contexts (e.g. multipl…

cs.AI2023★ 3 cited

The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents

Grgur Kovač, Rémy Portelas, Peter Ford Dominey +1

Developmental psychologists have long-established the importance of socio-cognitive abilities in human intelligence. These abilities enable us to enter, participate and benefit fro…

cs.CL2023★ 9 cited

Large Language Models as Superpositions of Cultural Perspectives

Grgur Kovač, Masataka Sawayama, Rémy Portelas +3

Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with…

cs.LG2021★ 1 cited

SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents

Grgur Kovač, Rémy Portelas, Katja Hofmann +1

Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI. Within the Deep Reinforcement Learning (DRL) fi…

cs.LG2021

SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents

Grgur Kovač, Rémy Portelas, Katja Hofmann +1

Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI. This problem motivated many research directions…