Kunvar Thaman has emerged as a notable name in machine learning circles after his solo-authored paper, Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use, was accepted to ICML ...
From large language models to brain-machine interfaces, students work with faculty on cutting-edge research. UT College of Natural Sciences undergraduates Prasann Singhal, Nihita Sarma, Shankar ...
Kunvar Thaman’s study on “reward hacking” in AI agents earns rare solo acceptance at one of the world’s top machine learning conferences.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results