Zobrazeno 1 - 10
of 6 909
pro vyhledávání: '"Wan, Yi"'
We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at commonly used di
Externí odkaz:
http://arxiv.org/abs/2405.09999
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts their practica
Externí odkaz:
http://arxiv.org/abs/2405.00338
Autor:
He, Xiang, Song, Weiye, Wang, Yiming, Poiesi, Fabio, Yi, Ji, Desai, Manishi, Xu, Quanqing, Yang, Kongzheng, Wan, Yi
Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as an important tool for diagnosing ophthalmic diseases. However, it is challenging to achieve accurate segmentation due to low contra
Externí odkaz:
http://arxiv.org/abs/2404.16346
The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize spatial info
Externí odkaz:
http://arxiv.org/abs/2403.01123
Autor:
Wan, Yi
Recently, atomically thin two-dimensional (2D) transition metal dichalcogenides (TMDCs) materials have drawn significant attention due to their unique optical and electrical properties1, 2. This offers unique opportunities for the next-generation ele
Externí odkaz:
http://hdl.handle.net/10754/669688
In this paper, we study asynchronous stochastic approximation algorithms without communication delays. Our main contribution is a stability proof for these algorithms that extends a method of Borkar and Meyn by accommodating more general noise condit
Externí odkaz:
http://arxiv.org/abs/2312.15091
Autor:
Zhu, Zheqing, Braz, Rodrigo de Salvo, Bhandari, Jalaj, Jiang, Daniel, Wan, Yi, Efroni, Yonathan, Wang, Liyuan, Xu, Ruiyang, Guo, Hongbo, Nikulkov, Alex, Korenkevych, Dmytro, Dogan, Urun, Cheng, Frank, Wu, Zheng, Xu, Wanqiao
Reinforcement Learning (RL) offers a versatile framework for achieving long-term goals. Its generality allows us to formalize a wide range of problems that real-world intelligent systems encounter, such as dealing with delayed rewards, handling parti
Externí odkaz:
http://arxiv.org/abs/2312.03814
Autor:
Wu, Xidong, Lin, Wan-Yi, Willmott, Devin, Condessa, Filipe, Huang, Yufei, Li, Zhenzhen, Ganesh, Madan Ravi
Federated Learning (FL) is a distributed training paradigm that enables clients scattered across the world to cooperatively learn a global model without divulging confidential data. However, FL faces a significant challenge in the form of heterogeneo
Externí odkaz:
http://arxiv.org/abs/2311.08479
Autor:
Qiu, Chen, Li, Xingyu, Mummadi, Chaithanya Kumar, Ganesh, Madan Ravi, Li, Zhenzhen, Peng, Lu, Lin, Wan-Yi
Prompt learning for vision-language models, e.g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons. Existing prompt learning techniques re
Externí odkaz:
http://arxiv.org/abs/2310.06123
The increasing popularity of compact and inexpensive cameras, e.g.~dash cameras, body cameras, and cameras equipped on robots, has sparked a growing interest in detecting anomalies within dynamic scenes recorded by moving cameras. However, existing r
Externí odkaz:
http://arxiv.org/abs/2308.07050