← Search

Ji Won Yoon

8 accepted papers

2026

BiCycle: Group-wise Recursive Transformer Based on ASR Mechanism

AAAI 2026technical

Recursive transformer (RT) is a promising parameter-sharing technique for reducing computational burden of large-scale model. While RT has been successfully applied to large language models (LLMs), its effectiveness in automatic speech recognition (ASR) remains limited, despite the parallel trend of

Cited by 0SourcePDFScholar
2026

GrayKD: Distilling Better Knowledge from Black-box LLM via Multi-rationale Injection

AAAI 2026technical

Knowledge distillation (KD) is a promising compression technique for reducing the computational burden of large language models (LLMs). Depending on access to the teacher model’s internal parameters, KD is typically categorized into white-box and black-box KD. While white-box KD benefits from full a

Cited by 0SourcePDFScholar
2025

FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning

ICASSP 2025accepted

Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker verification (ASV) systems to spoofing attacks. A key challenge in this task is generalizing models to detect unseen, out-of…

Cited by 0SourceScholar
2024

Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation

NeurIPS 2024poster

Single-cell RNA sequencing (scRNA-seq) technologies enable the exploration of cellular heterogeneity and facilitate the construction of cell atlases. However, scRNA-seq data often contain a large portion of missing values (false zeros) or noisy values, hindering downstream analyses. To recover these…

2023

EM-Network: Oracle Guided Self-distillation for Sequence Learning

ICML 2023poster

We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning. In contrast to conventional methods, it is trained with oracle guidance, which is derived from the target sequence. Since the oracle guida…

Cited by 3SourcePDFScholar