Zobrazeno 1 - 10
of 6 398
pro vyhledávání: '"An, Taeyoung"'
Mamba has recently emerged as a promising alternative to Transformers, offering near-linear complexity in processing sequential data. However, while channels in time series (TS) data have no specific order in general, recent studies have adopted Mamb
Externí odkaz:
http://arxiv.org/abs/2410.23356
Recent advancements in foundation models have been successfully extended to the time series (TS) domain, facilitated by the emergence of large-scale TS datasets. However, previous efforts have primarily focused on designing model architectures to add
Externí odkaz:
http://arxiv.org/abs/2410.23222
Advances in diffusion models for generative artificial intelligence have recently propagated to the time series (TS) domain, demonstrating state-of-the-art performance on various tasks. However, prior works on TS diffusion models often borrow the fra
Externí odkaz:
http://arxiv.org/abs/2410.14488
Autor:
Kim, Hyeonah, Kim, Minsu, Yun, Taeyoung, Choi, Sanghyeok, Bengio, Emmanuel, Hernández-García, Alex, Park, Jinkyoo
Designing biological sequences with desired properties is a significant challenge due to the combinatorially vast search space and the high cost of evaluating each candidate sequence. To address these challenges, reinforcement learning (RL) methods,
Externí odkaz:
http://arxiv.org/abs/2410.04461
Recently introduced dialogue systems have demonstrated high usability. However, they still fall short of reflecting real-world conversation scenarios. Current dialogue systems exhibit an inability to replicate the dynamic, continuous, long-term inter
Externí odkaz:
http://arxiv.org/abs/2410.02503
Autor:
Kim, Minsu, Choi, Sanghyeok, Yun, Taeyoung, Bengio, Emmanuel, Feng, Leo, Rector-Brooks, Jarrid, Ahn, Sungsoo, Park, Jinkyoo, Malkin, Nikolay, Bengio, Yoshua
Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential decision-makin
Externí odkaz:
http://arxiv.org/abs/2410.01432
Autor:
Yun, Taeyoung, Lee, Kanghoon, Yun, Sujin, Kim, Ilmyung, Jung, Won-Woo, Kwon, Min-Cheol, Choi, Kyujin, Lee, Yoohyeon, Park, Jinkyoo
Complex urban road networks with high vehicle occupancy frequently face severe traffic congestion. Designing an effective strategy for managing multiple traffic lights plays a crucial role in managing congestion. However, most current traffic light m
Externí odkaz:
http://arxiv.org/abs/2408.07327
Autor:
Kim, Taeyoung, Kang, Myungjoo
The Rectified Power Unit (RePU) activation functions, unlike the Rectified Linear Unit (ReLU), have the advantage of being a differentiable function when constructing neural networks. However, it can be experimentally observed when deep layers are st
Externí odkaz:
http://arxiv.org/abs/2408.02697
Autor:
Kumarasubramanian, Harish, Ravindran, Prasanna Venkat, Liu, Ting-Ran, Song, Taeyoung, Surendran, Mythili, Chen, Huandong, Buragohain, Pratyush, Tung, I-Cheng, Gupta, Arnab Sen, Steinhardt, Rachel, Young, Ian A., Shao, Yu-Tsun, Khan, Asif Islam, Ravichandran, Jayakanth
Ferroelectricity is characterized by the presence of spontaneous and switchable macroscopic polarization. Scaling limits of ferroelectricity have been of both fundamental and technological importance, but the probes of ferroelectricity have often bee
Externí odkaz:
http://arxiv.org/abs/2407.13953
Optimizing complex and high-dimensional black-box functions is ubiquitous in science and engineering fields. Unfortunately, the online evaluation of these functions is restricted due to time and safety constraints in most cases. In offline model-base
Externí odkaz:
http://arxiv.org/abs/2407.01624