2 papers
cs.CL2026
SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences
Jungyoub Cha, Hyunjong Kim, Sungzoon Cho
Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant dro…
cs.HC2024
CHOP: Integrating ChatGPT into EFL Oral Presentation Practice
Jungyoub Cha, Jieun Han, Haneul Yoo +1
English as a Foreign Language (EFL) students often struggle to deliver oral presentations due to a lack of reliable resources and the limited effectiveness of instructors' feedback…