4 papers
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
Minseok Kang, Hyunwoo Kim, Chanyoung Kim +3
Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal tasks through large-scale pre-training, yet their rapidly increasing computational a…
Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations
Chanyoung Kim, Myeonghwan Seong, Yujin Kim +2
Partial differential equations (PDEs) are central to modeling physical and engineering systems, but repeatedly solving parametric PDEs remains computationally expensive. Operator l…
KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context
Nahyun Lee, Guijin Son, Hyunwoo Ko +4
We introduce KMMMU, a native Korean benchmark for evaluating multimodal understanding in Korean cultural and institutional settings. KMMMU contains 3,466 questions from exams nativ…
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
Chanyoung Kim, Minwoo Kim, Minseok Kang +2
Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language backbones. However, in downstream robotic settings,…