Zobrazeno 1 - 10
of 401
pro vyhledávání: '"Park, Seongmin A."'
Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendly processing. However, dense pillar processing fundamentally wastes co
Externí odkaz:
http://arxiv.org/abs/2408.13798
The rapid advancement of large language models (LLMs) has facilitated their transformation into conversational chatbots that can grasp contextual nuances and generate pertinent sentences, closely mirroring human values through advanced techniques suc
Externí odkaz:
http://arxiv.org/abs/2407.03051
We present HyperSum, an extractive summarization framework that captures both the efficiency of traditional lexical summarization and the accuracy of contemporary neural approaches. HyperSum exploits the pseudo-orthogonality that emerges when randoml
Externí odkaz:
http://arxiv.org/abs/2405.09765
We present HyperSeg, a hyperdimensional computing (HDC) approach to unsupervised dialogue topic segmentation. HDC is a class of vector symbolic architectures that leverages the probabilistic orthogonality of randomly drawn vectors at extremely high d
Externí odkaz:
http://arxiv.org/abs/2308.10464
Collaborative filtering (CF) is a pivotal technique in modern recommender systems. The learning process of CF models typically consists of three components: interaction encoder, loss function, and negative sampling. Although many existing studies hav
Externí odkaz:
http://arxiv.org/abs/2308.06091
Because implicit user feedback for the collaborative filtering (CF) models is biased toward popular items, CF models tend to yield recommendation lists with popularity bias. Previous studies have utilized inverse propensity weighting (IPW) or causal
Externí odkaz:
http://arxiv.org/abs/2305.12768
Autor:
Lee, Minjae, Park, Seongmin, Kim, Hyungmin, Yoon, Minyong, Lee, Janghwan, Choi, Jun Won, Kim, Nam Sung, Kang, Mingu, Choi, Jungwook
3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements. PointPillars, a widely adopted bird's-eye view (BEV)
Externí odkaz:
http://arxiv.org/abs/2305.07522
Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the implementation co
Externí odkaz:
http://arxiv.org/abs/2302.11812
Uniform-precision neural network quantization has gained popularity since it simplifies densely packed arithmetic unit for high computing capability. However, it ignores heterogeneous sensitivity to the impact of quantization errors across the layers
Externí odkaz:
http://arxiv.org/abs/2212.10878
Autor:
Jeong, Jaeyeong1,2 (AUTHOR) jaeyeong@sju.ac.kr, Park, Seongmin3 (AUTHOR) smpark@kisa.or.kr, Lim, Joonhyung3 (AUTHOR) lim@kisa.or.kr, Kang, Jiwon1,4 (AUTHOR) jwkang@sejong.ac.kr, Shin, Dongil1 (AUTHOR) dshin@sejong.ac.kr, Shin, Dongkyoo1,2,4 (AUTHOR) shindk@sejong.ac.kr
Publikováno v:
Symmetry (20738994). Sep2024, Vol. 16 Issue 9, p1220. 14p.
