14 papers
An Interface Green's Function Framework for Complete Discrete Analysis of Discontinuous Galerkin Methods
Haitao Leng, Weifeng Qiu
Pointwise error analysis of discontinuous Galerkin (DG) methods has received considerable attention during the past two decades. Existing analyses establish optimal error estimates…
Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
Hojun Choi, Seulbin Hwang, Daejung Kim +4
Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving. Despite recent progress, state-of-the-art methods remain c…
MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
Hojun Choi, Youngsun Lim, Jaeyo Shin +1
Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseud…
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
Jiho Choi, Seonho Lee, Seojeong Park +1
Multi-view 3D Visual Question Answering (MV3D-VQA) requires integrating partial observations into a coherent 3D scene representation and selecting informative viewpoints for multi-…
Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
Inha Kang, Eunki Kim, Wonjeong Ryu +7
Accurate long horizon forecasting of particulate matter (PM) concentration fields is essential for operational public health decisions. However, achieving reliable forecasts remain…
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
Inha Kang, Youngsun Lim, Seonho Lee +3
State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly seve…