Zobrazeno 1 - 10
of 4 552
pro vyhledávání: '"An, Yunho"'
LLMs have emerged as a promising tool for assisting individuals in diverse text-generation tasks, including job-related texts. However, LLM-generated answers have been increasingly found to exhibit gender bias. This study evaluates three LLMs (GPT-3.
Externí odkaz:
http://arxiv.org/abs/2410.20739
Masked generative models (MGMs) have shown impressive generative ability while providing an order of magnitude efficient sampling steps compared to continuous diffusion models. However, MGMs still underperform in image synthesis compared to recent we
Externí odkaz:
http://arxiv.org/abs/2410.13136
We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We address two key challenges in offline RL: out-of-distribution samples a
Externí odkaz:
http://arxiv.org/abs/2410.11338
Effective long-term strategies enable AI systems to navigate complex environments by making sequential decisions over extended horizons. Similarly, reinforcement learning (RL) agents optimize decisions across sequences to maximize rewards, even witho
Externí odkaz:
http://arxiv.org/abs/2410.11324
Autor:
Yu, Seonghoon, Jung, Ilchae, Han, Byeongju, Kim, Taeoh, Kim, Yunho, Wee, Dongyoon, Son, Jeany
Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g., Swin transformer and BERT (u
Externí odkaz:
http://arxiv.org/abs/2408.15521
Autor:
Kim, Yunho, Lee, Jeong Hyun, Lee, Choongin, Mun, Juhyeok, Youm, Donghoon, Park, Jeongsoo, Hwangbo, Jemin
For reliable autonomous robot navigation in urban settings, the robot must have the ability to identify semantically traversable terrains in the image based on the semantic understanding of the scene. This reasoning ability is based on semantic trave
Externí odkaz:
http://arxiv.org/abs/2406.02989
Autor:
Harma, Simla Burcu, Chakraborty, Ayan, Kostenok, Elizaveta, Mishin, Danila, Ha, Dongho, Falsafi, Babak, Jaggi, Martin, Liu, Ming, Oh, Yunho, Subramanian, Suvinay, Yazdanbakhsh, Amir
The increasing size of deep neural networks necessitates effective model compression to improve computational efficiency and reduce their memory footprint. Sparsity and quantization are two prominent compression methods that have individually demonst
Externí odkaz:
http://arxiv.org/abs/2405.20935
Autor:
Halder, Suman, Shin, Yunho, Peng, Yidan, Wang, Long, Duan, Liye, Schmalenberg, Paul, Qin, Guangkui, Gao, Yuxi, Dede, Ercan M., Yang, Deng-Ke, Rodrigues, Sean P.
In the past decade, display technology has been reimagined to meet the needs of the virtual world. By mapping information onto a scene through a transparent display, users can simultaneously visualize both the real world and layers of virtual element
Externí odkaz:
http://arxiv.org/abs/2403.13831
Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs, achieving rotati
Externí odkaz:
http://arxiv.org/abs/2401.06159
Appropriate weight initialization settings, along with the ReLU activation function, have become cornerstones of modern deep learning, enabling the training and deployment of highly effective and efficient neural network models across diverse areas o
Externí odkaz:
http://arxiv.org/abs/2311.03733