Zobrazeno 1 - 10
of 1 795
pro vyhledávání: '"Le Long"'
Publikováno v:
Journal of Applied and Computational Mechanics, Vol 11, Iss 1, Pp 55-72 (2025)
This paper presents research on raising the efficiency and pressure of centrifugal fans at different speed ranges. This problem is related to the incompatibility of the fan characteristics with the speed conditions of the impeller and flow conditions
Externí odkaz:
https://doaj.org/article/2f0356b9935947c8a589f0e40351a00a
Autor:
Chen, Justin Chih-Yao, Wang, Zifeng, Palangi, Hamid, Han, Rujun, Ebrahimi, Sayna, Le, Long, Perot, Vincent, Mishra, Swaroop, Bansal, Mohit, Lee, Chen-Yu, Pfister, Tomas
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as
Externí odkaz:
http://arxiv.org/abs/2411.19865
Autor:
Ding, Tong, Wagner, Sophia J., Song, Andrew H., Chen, Richard J., Lu, Ming Y., Zhang, Andrew, Vaidya, Anurag J., Jaume, Guillaume, Shaban, Muhammad, Kim, Ahrong, Williamson, Drew F. K., Chen, Bowen, Almagro-Perez, Cristina, Doucet, Paul, Sahai, Sharifa, Chen, Chengkuan, Komura, Daisuke, Kawabe, Akihiro, Ishikawa, Shumpei, Gerber, Georg, Peng, Tingying, Le, Long Phi, Mahmood, Faisal
The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning (SSL). Howe
Externí odkaz:
http://arxiv.org/abs/2411.19666
In Federated Learning (FL), training is conducted on client devices, typically with limited computational resources and storage capacity. To address these constraints, we propose an automatic pruning scheme tailored for FL systems. Our solution impro
Externí odkaz:
http://arxiv.org/abs/2411.01759
Autor:
Xu, Wenda, Han, Rujun, Wang, Zifeng, Le, Long T., Madeka, Dhruv, Li, Lei, Wang, William Yang, Agarwal, Rishabh, Lee, Chen-Yu, Pfister, Tomas
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the knowledge gaps bet
Externí odkaz:
http://arxiv.org/abs/2410.11325
Autor:
Le, Long, Xie, Jason, Liang, William, Wang, Hung-Ju, Yang, Yue, Ma, Yecheng Jason, Vedder, Kyle, Krishna, Arjun, Jayaraman, Dinesh, Eaton, Eric
Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader
Externí odkaz:
http://arxiv.org/abs/2410.13882
Autor:
Truong, Vu Tuan, Le, Long Bao
Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored DMs consist
Externí odkaz:
http://arxiv.org/abs/2409.13945
Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they potentially are
Externí odkaz:
http://arxiv.org/abs/2408.03400
Autor:
Jaume, Guillaume, Vaidya, Anurag, Zhang, Andrew, Song, Andrew H., Chen, Richard J., Sahai, Sharifa, Mo, Dandan, Madrigal, Emilio, Le, Long Phi, Mahmood, Faisal
Developing self-supervised learning (SSL) models that can learn universal and transferable representations of H&E gigapixel whole-slide images (WSIs) is becoming increasingly valuable in computational pathology. These models hold the potential to adv
Externí odkaz:
http://arxiv.org/abs/2408.02859
Autor:
Wang, Zilong, Wang, Zifeng, Le, Long, Zheng, Huaixiu Steven, Mishra, Swaroop, Perot, Vincent, Zhang, Yuwei, Mattapalli, Anush, Taly, Ankur, Shang, Jingbo, Lee, Chen-Yu, Pfister, Tomas
Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses. Recent RAG advancements focus on improving retrieval outcomes th
Externí odkaz:
http://arxiv.org/abs/2407.08223