8 papers
Domain-Adaptive Data Assimilation for Global AI Weather Forecasting
Minseok Seo, Noah Brenowitz, Doyi Kim +2
AI weather forecasting models are commonly trained on the ERA5 reanalysis, which is unavailable in real time. Operational deployment therefore relies on initial conditions produced…
RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
Yeeun Seong, Doyi Kim, Minseok Seo +1
In precipitation forecasting, not only accuracy but also temporal resolution is critical. However, increasing temporal resolution is constrained by observational limitations and th…
Query-Conditioned Test-Time Self-Training for Large Language Models
Chaehee Song, Minseok Seo, Yeeun Seong +2
Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often improved by allocating more computation at inference time. While such test…
StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion
Minseok Seo, Wonjun Lee, Jaehyuk Jang +1
Monocular depth foundation models generalize across diverse scenes, but recovering accurate metric depth consistent with a target sensor remains challenging under sensor variation…
Station2Radar: query conditioned gaussian splatting for precipitation field
Doyi Kim, Minseok Seo, Changick Kim
Precipitation forecasting relies on heterogeneous data. Weather radar is accurate, but coverage is geographically limited and costly to maintain. Weather stations provide accurate…
Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
Minseok Seo, Mark Hamilton, Changick Kim
We present \textbf{Upsample Anything}, a lightweight test-time optimization (TTO) framework that restores low-resolution features to high-resolution, pixel-wise outputs without any…
BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
Youngju Yoo, Seho Kim, Changick Kim
3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotati…
1st Place in ICCV 2023 Workshop Challenge Track 1 on Resource Efficient Deep Learning for Computer Vision: Budgeted Model Training Challenge
Youngjun Kwak, Seonghun Jeong, Yunseung Lee +1
The budgeted model training challenge aims to train an efficient classification model under resource limitations. To tackle this task in ImageNet-100, we describe a simple yet effe…