5 papers
TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference
Jiyoung Park, Hankyu Jang, Changseok Song +1
Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads. We present TIDE (Temporal Incremen…
Leveraging Textual Compositional Reasoning for Robust Change Captioning
Kyu Ri Park, Jiyoung Park, Seong Tae Kim +2
Change captioning aims to describe changes between a pair of images. However, existing works rely on visual features alone, which often fail to capture subtle but meaningful change…
Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
Junghwan Lim, Gangwon Jo, Sungmin Lee +16
We introduce Llama-3-Motif, a language model consisting of 102 billion parameters, specifically designed to enhance Korean capabilities while retaining strong performance in Englis…
Probabilistic U-Net with Kendall Shape Spaces for Geometry-Aware Segmentations of Images
Jiyoung Park, Günay Doğan
One of the fundamental problems in computer vision is image segmentation, the task of detecting distinct regions or objects in given images. Deep Neural Networks (DNN) have been sh…
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
Jiyoung Park, Ian Pelakh, Stephan Wojtowytsch
We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number o…