Nam Hyeon-Woo*, Moon Ye-Bin*, Wonseok Choi, Tae-Hyun Oh, BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models, Under Review
* equal contribution

• Evaluation

Nam Hyeon-Woo*, Moon Ye-Bin*, Wonseok Choi,  Lee Hyun, Tae-Hyun Oh,  VLM’s Eye Examination: Instruct and Inspect Visual Competency of Vision Language Model, Under Review
* equal contribution

• Evaluation, Science of deep learning

Lee Chae-Yeon*, Nam Hyeon-Woo*, Tae-Hyun Oh, COARA: Efficient Correlation-Aware Uncertainty Modeling in Hand Pose Estimation,  Under Review
* equal contribution

• Robustness, Uncertatiny

Moon Ye-Bin*, Nam Hyeon-Woo*, Wonseok Choi, Nayeong Kim, Suha Kwak, Tae-Hyun Oh, Exploiting Synthetic Data for Data Imbalance Problems: Baselines from a Data Perspective, ICCV 2023 workshop
* equal contribution

• Robustness, Data augmentation

Nam Hyeon-Woo, Kim Yu-Ji, Byeongho Heo, Dongyoon Han, Seong Joon Oh, Tae-Hyun Oh, Scratching Visual Transformer's Back with Uniform Attention, ICCV 2023 [project page]
(Jo wonjun draws the left figure)

• Science of deep learning

Kwon Byung-Ki, Nam Hyeon-Woo, Ji-Yun Kim, Tae-Hyun Oh, DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline, ICLR 2023

• Data augmentation, Science of deep learning

Nam Hyeon-Woo, Moon Ye-Bin, and Tae-Hyun Oh, FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning, ICLR 2022

• Large scale optimization, Privacy