Zobrazeno 1 - 10
of 1 489
pro vyhledávání: '"Arandjelovic A"'
Autor:
Guo, Zhongliang, Fang, Lei, Lin, Jingyu, Qian, Yifei, Zhao, Shuai, Wang, Zeyu, Dong, Junhao, Chen, Cunjian, Arandjelović, Ognjen, Lau, Chun Pong
Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have revolutionized image synthesis and manipulation. However, these generative techniques raises concerns about data misappropriation and intellectual property infrin
Externí odkaz:
http://arxiv.org/abs/2408.10901
Autor:
Arandjelović, Aleksandar, Shevchenko, Pavel V., Matsui, Tomoko, Murakami, Daisuke, Myrvoll, Tor A.
Stochastic versions of recursive integrated climate-economy assessment models are essential for studying and quantifying policy decisions under uncertainty. However, as the number of stochastic shocks increases, solving these models as dynamic progra
Externí odkaz:
http://arxiv.org/abs/2408.09642
We consider an insurance company which faces financial risk in the form of insurance claims and market-dependent surplus fluctuations. The company aims to simultaneously control its terminal wealth (e.g. at the end of an accounting period) and the ru
Externí odkaz:
http://arxiv.org/abs/2408.06168
Pre-trained Language Models (LMs) exhibit strong zero-shot and in-context learning capabilities; however, their behaviors are often difficult to control. By utilizing Reinforcement Learning from Human Feedback (RLHF), it is possible to fine-tune unsu
Externí odkaz:
http://arxiv.org/abs/2405.20053
Autor:
Brookes, Otto, Mirmehdi, Majid, Stephens, Colleen, Angedakin, Samuel, Corogenes, Katherine, Dowd, Dervla, Dieguez, Paula, Hicks, Thurston C., Jones, Sorrel, Lee, Kevin, Leinert, Vera, Lapuente, Juan, McCarthy, Maureen S., Meier, Amelia, Murai, Mizuki, Normand, Emmanuelle, Vergnes, Virginie, Wessling, Erin G., Wittig, Roman M., Langergraber, Kevin, Maldonado, Nuria, Yang, Xinyu, Zuberbuhler, Klaus, Boesch, Christophe, Arandjelovic, Mimi, Kuhl, Hjalmar, Burghardt, Tilo
We present the PanAf20K dataset, the largest and most diverse open-access annotated video dataset of great apes in their natural environment. It comprises more than 7 million frames across ~20,000 camera trap videos of chimpanzees and gorillas collec
Externí odkaz:
http://arxiv.org/abs/2401.13554
Autor:
Guo, Zhongliang, Dong, Junhao, Qian, Yifei, Wang, Kaixuan, Li, Weiye, Guo, Ziheng, Wang, Yuheng, Li, Yanli, Arandjelović, Ognjen, Fang, Lei
Neural style transfer (NST) generates new images by combining the style of one image with the content of another. However, unauthorized NST can exploit artwork, raising concerns about artists' rights and motivating the development of proactive protec
Externí odkaz:
http://arxiv.org/abs/2401.09673
This paper introduces a novel Parameter-Efficient Fine-Tuning (PEFT) framework for multi-modal, multi-task transfer learning with pre-trained language models. PEFT techniques such as LoRA, BitFit and IA3 have demonstrated comparable performance to fu
Externí odkaz:
http://arxiv.org/abs/2312.08900
Autor:
Wölflein, Georg, Ferber, Dyke, Meneghetti, Asier R., Nahhas, Omar S. M. El, Truhn, Daniel, Carrero, Zunamys I., Harrison, David J., Arandjelović, Ognjen, Kather, Jakob Nikolas
Weakly supervised whole slide image classification is a key task in computational pathology, which involves predicting a slide-level label from a set of image patches constituting the slide. Constructing models to solve this task involves multiple de
Externí odkaz:
http://arxiv.org/abs/2311.11772
To alleviate the heavy annotation burden for training a reliable crowd counting model and thus make the model more practicable and accurate by being able to benefit from more data, this paper presents a new semi-supervised method based on the mean te
Externí odkaz:
http://arxiv.org/abs/2310.10352
We investigate insurance purchases when bequest motives are age-varying and life insurance and life annuities both carry loads. The existing life cycle literature assumes bequests are normal goods without being either necessities or luxuries. Much of
Externí odkaz:
http://arxiv.org/abs/2310.06274