activity
20242026
collaborators

6 papers

cs.CV2026

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Cheolhong Min, Jaeyun Jung, Daeun Lee +5

Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on st…

cs.CV2026

IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation

Sunghyun Baek, Jaemyung Yu, Seunghee Koh +3

Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich repr…

cs.CV2026

UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting

Geonuk Kim, Minhoi Kim, Kangil Lee +5

Although industrial inspection systems should be capable of recognizing unprecedented defects, most existing approaches operate under a closed-set assumption, which prevents them f…

cs.RO2025

Convergent Functions, Divergent Forms

Hyeonseong Jeon, Ainaz Eftekhar, Aaron Walsman +3

We introduce LOKI, a compute-efficient framework for co-designing morphologies and control policies that generalize across unseen tasks. Inspired by biological adaptation -- where…

cs.AI2025

Tree-Guided Diffusion Planner

Hyeonseong Jeon, Cheolhong Min, Jaesik Park

Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. Standard gradient guidance typically performs optimally…

cs.LG2024

Learning to Continually Learn with the Bayesian Principle

Soochan Lee, Hyeonseong Jeon, Jaehyeon Son +1

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non…