Zobrazeno 1 - 10
of 1 938
pro vyhledávání: '"Kim, JinWoo"'
In this work, we investigate a method for simulation-free training of Neural Ordinary Differential Equations (NODEs) for learning deterministic mappings between paired data. Despite the analogy of NODEs as continuous-depth residual networks, their ap
Externí odkaz:
http://arxiv.org/abs/2410.22918
Applications like program synthesis sometimes require proving that a property holds for all of the infinitely many programs described by a grammar - i.e., an inductively defined set of programs. Current verification frameworks overapproximate program
Externí odkaz:
http://arxiv.org/abs/2410.16102
Autor:
Hu, Seungbeom, Park, ChanJun, Ferraiuolo, Andrew, Ko, Sang-Ki, Kim, Jinwoo, Song, Haein, Kim, Jieung
Determining the optimal size of a neural network is critical, as it directly impacts runtime performance and memory usage. Pruning is a well-established model compression technique that reduces the size of neural networks while mathematically guarant
Externí odkaz:
http://arxiv.org/abs/2408.13482
In recent times, the need for effective super-resolution (SR) techniques has surged, especially for large-scale images ranging 2K to 8K resolutions. For DNN-based SISR, decomposing images into overlapping patches is typically necessary due to computa
Externí odkaz:
http://arxiv.org/abs/2407.21448
We revisit a simple idea for machine learning on graphs, where a random walk on a graph produces a machine-readable record, and this record is processed by a deep neural network to directly make vertex-level or graph-level predictions. We refer to th
Externí odkaz:
http://arxiv.org/abs/2407.01214
Autor:
Kim, Jinwoo
This paper considers program synthesis in the context of computational hardness, asking the question: How hard is it to determine whether a given synthesis problem has a solution or not? To answer this question, this paper studies program synthesis f
Externí odkaz:
http://arxiv.org/abs/2405.16997
We study law enforcement guided by data-informed predictions of "hot spots" for likely criminal offenses. Such "predictive" enforcement could lead to data being selectively and disproportionately collected from neighborhoods targeted for enforcement
Externí odkaz:
http://arxiv.org/abs/2405.04764
Autor:
Kim, Yoochan, Kim, Kihyun, Cho, Yonghyeon, Kim, Jinwoo, Khan, Awais, Kang, Ki-Dong, An, Baik-Song, Cha, Myung-Hoon, Kim, Hong-Yeon, Kim, Youngjae
Distributed Deep Learning (DDL), as a paradigm, dictates the use of GPU-based clusters as the optimal infrastructure for training large-scale Deep Neural Networks (DNNs). However, the high cost of such resources makes them inaccessible to many users.
Externí odkaz:
http://arxiv.org/abs/2403.05861
White balance (WB) algorithms in many commercial cameras assume single and uniform illumination, leading to undesirable results when multiple lighting sources with different chromaticities exist in the scene. Prior research on multi-illuminant WB typ
Externí odkaz:
http://arxiv.org/abs/2402.18277
Automated verification of all members of a (potentially infinite) set of programs has the potential to be useful in program synthesis, as well as in verification of dynamically loaded code, concurrent code, and language properties. Existing technique
Externí odkaz:
http://arxiv.org/abs/2401.13244