no code implementations • 16 Feb 2024 • Yoonjeong Park, HyunJin Kim, Chanyeol Choi, JunSeong Kim, Jy-yong Sohn
The basic idea of CoT is to let LLMs break down their thought processes step-by-step by putting exemplars in the input prompt.
no code implementations • 11 Jan 2024 • HyunJin Kim, Minhyuk Sung
Our proposed task adaptation method finetunes a 2D bounding box prediction model with an objective function for 3D segmentation.
1 code implementation • 14 Nov 2023 • HyunJin Kim, Young Jin Kim, JinYeong Bak
PEMA integrates with context representations from test data during inference to perform downstream tasks.
no code implementations • 3 Nov 2023 • Tuyen P. Le, Hieu T. Nguyen, Seungyeol Baek, Taeyoun Kim, Jungwoo Lee, Seongjung Kim, HyunJin Kim, Misu Jung, Daehoon Kim, Seokyong Lee, Daewoo Choi
Macro placement is a critical phase in chip design, which becomes more intricate when involving general rectilinear macros and layout areas.
no code implementations • 4 Sep 2023 • Gyeongdong Yang, Yungwook Kwon, HyunJin Kim
This paper is motivated by the idea that the data itself from early attention stages can have important meaning for the final classification.
no code implementations • 26 Jun 2022 • HyunJin Kim, Jungwoo Shin, Alberto A. Del Barrio
In each quantization step, the trained weights of a model are used to initialize the weights of the next model with the quantization bit depth reduced by one.
no code implementations • CVPR 2022 • Jihyun Lee, Minhyuk Sung, HyunJin Kim, Tae-Kyun Kim
We propose a framework that can deform an object in a 2D image as it exists in 3D space.
1 code implementation • 18 Feb 2021 • Raul Murillo, Alberto A. Del Barrio, Guillermo Botella, Min Soo Kim, HyunJin Kim, Nader Bagherzadeh
The Posit Number System was introduced in 2017 as a replacement for floating-point numbers.
1 code implementation • 20 Jul 2020 • Min Soo Kim, Alberto A. Del Barrio, HyunJin Kim, Nader Bagherzadeh
The approximate multiplication can reduce the cost of the underlying circuits so that CNN inferences can be performed more efficiently in hardware accelerators.