3 papers
cs.LG2026
Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Nayeon Kim, Hojin Lee, Yunju Bak +2
Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing their hyperparameters---partic…
cs.AI2025
Cognitive Weave: Synthesizing Abstracted Knowledge with a Spatio-Temporal Resonance Graph
Akash Vishwakarma, Hojin Lee, Mohith Suresh +4
The emergence of capable large language model (LLM) based agents necessitates memory architectures that transcend mere data storage, enabling continuous learning, nuanced reasoning…
cs.CL2025
Kanana: Compute-efficient Bilingual Language Models
Kanana LLM Team, Yunju Bak, Hojin Lee +26
We introduce Kanana, a series of bilingual language models that demonstrate exceeding performance in Korean and competitive performance in English. The computational cost of Kanana…