2 papers
cs.LG2026
Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control
David Golchinfar, Daryoush Vaziri, Alexander Marquardt
We present SauerkrautLM-Doom-MultiVec, a 1.3 million parameter model that plays the classic first-person shooter DOOM in real time, outperforming large language models up to 92,000…
cs.LG2024
Spectrum: Targeted Training on Signal to Noise Ratio
Eric Hartford, Lucas Atkins, Fernando Fernandes Neto +1
Efficiently post-training large language models remains a challenging task due to the vast computational resources required. We present Spectrum, a method that accelerates LLM trai…