Zobrazeno 1 - 10
of 3 332
pro vyhledávání: '"Pathmanathan A"'
Autor:
Pathmanathan, Pankayaraj, Sehwag, Udari Madhushani, Panaitescu-Liess, Michael-Andrei, Huang, Furong
With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmful behaviors. Existing backdoor
Externí odkaz:
http://arxiv.org/abs/2410.11283
Autor:
Kanagalingam, Heethanjan, Pathmanathan, Thenukan, Ketheeswaran, Navaneethan, Vathanakumar, Mokeeshan, Afham, Mohamed, Rodrigo, Ranga
Few-shot learning (FSL) aims to enable models to recognize novel objects or classes with limited labelled data. Feature generators, which synthesize new data points to augment limited datasets, have emerged as a promising solution to this challenge.
Externí odkaz:
http://arxiv.org/abs/2409.14141
Autor:
Pathmanathan, Dharini, Dabo, Issa-Mbenard, Khoo, Tzung Hsuen, Ali-Hassan, Alaa, Dabo-Niang, Sophie
In this article, we present the bivariate and multivariate functional Moran's I statistics and multivariate functional areal spatial principal component analysis (mfasPCA). These methods are the first of their kind in the field of multivariate areal
Externí odkaz:
http://arxiv.org/abs/2408.08630
Autor:
Panaitescu-Liess, Michael-Andrei, Che, Zora, An, Bang, Xu, Yuancheng, Pathmanathan, Pankayaraj, Chakraborty, Souradip, Zhu, Sicheng, Goldstein, Tom, Huang, Furong
Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as LLMs may inadvertently produce copyrighted material. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2407.17417
This study introduces an innovative methodology for mortality forecasting, which integrates signature-based methods within the functional data framework of the Hyndman-Ullah (HU) model. This new approach, termed the Hyndman-Ullah with truncated signa
Externí odkaz:
http://arxiv.org/abs/2407.15461
In this paper, we explore dimension reduction for time series of functional data within both stationary and non-stationary frameworks. We introduce a functional framework of generalized dynamic principal component analysis (GDPCA). The concept of GDP
Externí odkaz:
http://arxiv.org/abs/2407.16024
Autor:
Pathmanathan, Pankayaraj, Chakraborty, Souradip, Liu, Xiangyu, Liang, Yongyuan, Huang, Furong
Publikováno v:
ICML 2024 Workshop MHFAIA
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization (PPO) has le
Externí odkaz:
http://arxiv.org/abs/2406.12091
Image thumbnails are a valuable data source for fixation filtering, scanpath classification, and visualization of eye tracking data. They are typically extracted with a constant size, approximating the foveated area. As a consequence, the focused are
Externí odkaz:
http://arxiv.org/abs/2404.18680
In this work, we investigate the means of using curiosity on replay buffers to improve offline multi-task continual reinforcement learning when tasks, which are defined by the non-stationarity in the environment, are non labeled and not evenly expose
Externí odkaz:
http://arxiv.org/abs/2312.03177
Stock market indices are volatile by nature, and sudden shocks are known to affect volatility patterns. The autoregressive conditional heteroskedasticity (ARCH) and generalized ARCH (GARCH) models neglect structural breaks triggered by sudden shocks
Externí odkaz:
http://arxiv.org/abs/2310.02630