Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Pang, Linsey"'
Autor:
Yao, Huaiyuan, Da, Longchao, Nandam, Vishnu, Turnau, Justin, Liu, Zhiwei, Pang, Linsey, Wei, Hua
The integration of autonomous vehicles into urban traffic has great potential to improve efficiency by reducing congestion and optimizing traffic flow systematically. In this paper, we introduce CoMAL (Collaborative Multi-Agent LLMs), a framework des
Externí odkaz:
http://arxiv.org/abs/2410.14368
Sequential recommendation models have achieved state-of-the-art performance using self-attention mechanism. It has since been found that moving beyond only using item ID and positional embeddings leads to a significant accuracy boost when predicting
Externí odkaz:
http://arxiv.org/abs/2409.05022
Autor:
Messaoud, Safa, Mokeddem, Billel, Xue, Zhenghai, Pang, Linsey, An, Bo, Chen, Haipeng, Chawla, Sanjay
Learning expressive stochastic policies instead of deterministic ones has been proposed to achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy Reinforcement Learning (MaxEnt RL), the policy is modeled as an expres
Externí odkaz:
http://arxiv.org/abs/2405.00987
This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated. Through a novel evaluation
Externí odkaz:
http://arxiv.org/abs/2403.06013
A new method for outlier detection and generation is introduced by lifting data into the space of probability distributions which are not analytically expressible, but from which samples can be drawn using a neural generator. Given a mixture of unkno
Externí odkaz:
http://arxiv.org/abs/2012.12394
In this paper we present methods for exemplar based clustering with outlier selection based on the facility location formulation. Given a distance function and the number of outliers to be found, the methods automatically determine the number of clus
Externí odkaz:
http://arxiv.org/abs/1403.1329
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Data & Knowledge Engineering September 2013 87:357-373
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Web Technologies & Applications; 2013, p595-608, 14p