39 citations · 54 across the 9 of their papers we have counts for
12 papers
PhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models
Taekoan Yoo, Wonkyung Jung, Kyunghun Kim +1
World action models increasingly rely on pretrained video models assumed to capture physical dynamics for prediction, planning, and action generation. Existing evaluations assess p…
OpenAttention: One Percent Is Enough with Tail Proxies
Hyunwoo Yu, Jongbeom Lee, Hyunbin Kim +8
Sparse attention reads only a small subset of the key-value cache, and how to treat the unread tail remains a key challenge. Discarding the tail biases the output, and sampling it…
VIPA: Visual Informative Part Attention for Referring Image Segmentation
Yubin Cho, Hyunwoo Yu, Kyeongbo Kong +3
Referring Image Segmentation (RIS) aims to segment a target object described by a natural language expression. Existing methods have evolved by leveraging the vision information in…
Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
Jihyun Kim, Junho Park, Kyeongbo Kong +1
We present Programmable-Room, a framework which interactively generates and edits a 3D room mesh, given natural language instructions. For precise control of a room's each attribut…
AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild
Junho Park, Kyeongbo Kong, Suk-Ju Kang
Recently, there has been a significant amount of research conducted on 3D hand reconstruction to use various forms of human-computer interaction. However, 3D hand reconstruction in…
Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
Hyunwoo Yu, Yubin Cho, Beoungwoo Kang +3
We present an Encoder-Decoder Attention Transformer, EDAFormer, which consists of the Embedding-Free Transformer (EFT) encoder and the all-attention decoder leveraging our Embeddin…
AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
Jouwon Song, Kyeongbo Kong, Ye-In Park +2
Anomaly segmentation, which localizes defective areas, is an important component in large-scale industrial manufacturing. However, most recent researches have focused on anomaly de…
Mitigating Memorization in Sample Selection for Learning with Noisy Labels
Kyeongbo Kong, Junggi Lee, Youngchul Kwak +3
Because deep learning is vulnerable to noisy labels, sample selection techniques, which train networks with only clean labeled data, have attracted a great attention. However, if t…
Core-set Sampling for Efficient Neural Architecture Search
Jae-hun Shim, Kyeongbo Kong, Suk-Ju Kang
Neural architecture search (NAS), an important branch of automatic machine learning, has become an effective approach to automate the design of deep learning models. However, the m…
Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching
Kyeongbo Kong, Kyunghun Kim, Suk-Ju Kang
Conditional generative adversarial networks (cGANs) have demonstrated remarkable success due to their class-wise controllability and superior quality for complex generation tasks.…
Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation
Jou Won Song, Kyeongbo Kong, Ye In Park +1
Anomaly detection is a task that recognizes whether an input sample is included in the distribution of a target normal class or an anomaly class. Conventional generative adversaria…
Knowledge Distillation-aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback
Kyeongbo Kong, Woo-Jin Song, Moonsik Min
We propose a deep learning-based channel estimation, quantization, feedback, and precoding method for downlink multiuser multiple-input and multiple-output systems. In the proposed…