Junyoung Yeom — accepted AI-conference papers

2024

Compressed Context Memory for Online Language Model Interaction

Jang-Hyun Kim, Junyoung Yeom, Sangdoo Yun, Hyun Oh Song

ICLR 2024poster

This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands. As the context lengthens, the attention process demands increasing memory and computations, which in turn reduces the throughput of the language mode…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2023

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning

Seungyong Moon, Junyoung Yeom, Bumsoo Park, Hyun Oh Song

NeurIPS 2023poster

Discovering achievements with a hierarchical structure in procedurally generated environments presents a significant challenge. This requires an agent to possess a broad range of abilities, including generalization and long-term reasoning. Many prior methods have been built upon model-based or hiera…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗