3 papers
cs.CV2026
Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings
Mingi Kim, Yongjun Kim, Hyungki Kim
Recovering Parametric CAD sequences from raster-format 2D Computer-Aided Design (CAD) drawings accumulated prior to digital transformation is important for part reproduction and ma…
cs.CL2026
PARTREP: Learning What to Repeat for Decoder-only LLMs
Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim +1
While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in cont…
cs.CV2025
ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models
Seonghwan Park, Jaehyeon Jeong, Yongjun Kim +2
Recent studies have introduced various approaches for prompt-tuning black-box vision-language models, referred to as black-box prompt-tuning (BBPT). While BBPT has demonstrated con…