3 papers
cs.CV2026
DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs
Minyoung Park, Taehun Kong, Sangjun Ahn
Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visual tokens extracted from lon…
cs.CV2026
Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detection
Taehun Kong, Tae-Kyun Kim
Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and d…
cs.CV2024
Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariance
Minju Kang, Taehun Kong, Tae-Kyun Kim
Accurate 3D object detection is crucial for autonomous vehicles and robots to navigate and interact with the environment safely and effectively. Meanwhile, the performance of 3D de…