Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap
Dasol Choi, Joonyong Park, Daegon Yu +3
We introduce NOLLI, a procedurally generated English-Korean puzzle benchmark designed to diagnose where Korean performance gaps arise. It comprises 15 puzzle types (25 tasks; 7,500…
cs.CL2024
Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
Dasol Choi, Guijin Son, Soo Yong Kim +2
Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs o…