Introduces a benchmarking suite for compound AI applications to support cross-stack performance, cost, and resource analysis for hardware-software co-design.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
An LLM-driven role-playing game with implicit input enhancement and explicit practice tracking produced 21-27% better retention of slang phrases after one week than a standard AI-led virtual classroom.
citing papers explorer
-
Benchmarking Compound AI Applications for Hardware-Software Co-Design
Introduces a benchmarking suite for compound AI applications to support cross-stack performance, cost, and resource analysis for hardware-software co-design.
-
Game Master LLM: Task-Based Role-Playing for Natural Slang Learning
An LLM-driven role-playing game with implicit input enhancement and explicit practice tracking produced 21-27% better retention of slang phrases after one week than a standard AI-led virtual classroom.