2 papers
cs.CL2026
SelFusion: Self-distillation for Diffusion Language Models
Hyeongsoo Lim, Jinyoung Kim, Eunseo Seo +2
Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) large language models (LLMs), but their degraded generation quality limits practic…
eess.AS2023
Lightweight feature encoder for wake-up word detection based on self-supervised speech representation
Hyungjun Lim, Younggwan Kim, Kiho Yeom +4
Self-supervised learning method that provides generalized speech representations has recently received increasing attention. Wav2vec 2.0 is the most famous example, showing remarka…