Zobrazeno 1 - 10
of 23 615
pro vyhledávání: '"Yanai, A"'
Text-to-image (T2I) models are remarkable at generating realistic images based on textual descriptions. However, textual prompts are inherently underspecified: they do not specify all possible attributes of the required image. This raises two key que
Externí odkaz:
http://arxiv.org/abs/2410.22592
Autor:
Miranda, Lester James V., Wang, Yizhong, Elazar, Yanai, Kumar, Sachin, Pyatkin, Valentina, Brahman, Faeze, Smith, Noah A., Hajishirzi, Hannaneh, Dasigi, Pradeep
Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, directly collecting human preferences can be expensive, time-consuming, and can have high variance. An appealing alternative is to distil
Externí odkaz:
http://arxiv.org/abs/2410.19133
Autor:
Verma, Sahil, Rassin, Royi, Das, Arnav, Bhatt, Gantavya, Seshadri, Preethi, Shah, Chirag, Bilmes, Jeff, Hajishirzi, Hannaneh, Elazar, Yanai
Text-to-image models are trained using large datasets collected by scraping image-text pairs from the internet. These datasets often include private, copyrighted, and licensed material. Training models on such datasets enables them to generate images
Externí odkaz:
http://arxiv.org/abs/2410.15002
Autor:
He, Yan, Drozd, Vasyl, Ekawa, Hiroyuki, Escrig, Samuel, Gao, Yiming, Kasagi, Ayumi, Liu, Enqiang, Muneem, Abdul, Nakagawa, Manami, Nakazawa, Kazuma, Rappold, Christophe, Saito, Nami, Saito, Takehiko R., Sugimoto, Shohei, Taki, Masato, Tanaka, Yoshiki K., Wang, He, Yanai, Ayari, Yoshida, Junya, Zhang, Hongfei
A novel method was developed to detect double-$\Lambda$ hypernuclear events in nuclear emulsions using machine learning techniques. The object detection model, the Mask R-CNN, was trained using images generated by Monte Carlo simulations, image proce
Externí odkaz:
http://arxiv.org/abs/2409.01657
Autor:
Sainz, Oscar, García-Ferrero, Iker, Jacovi, Alon, Campos, Jon Ander, Elazar, Yanai, Agirre, Eneko, Goldberg, Yoav, Chen, Wei-Lin, Chim, Jenny, Choshen, Leshem, D'Amico-Wong, Luca, Dell, Melissa, Fan, Run-Ze, Golchin, Shahriar, Li, Yucheng, Liu, Pengfei, Pahwa, Bhavish, Prabhu, Ameya, Sharma, Suryansh, Silcock, Emily, Solonko, Kateryna, Stap, David, Surdeanu, Mihai, Tseng, Yu-Min, Udandarao, Vishaal, Wang, Zengzhi, Xu, Ruijie, Yang, Jinglin
The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where evaluation data is included in pre-training corpora u
Externí odkaz:
http://arxiv.org/abs/2407.21530
Autor:
Sharma, Rashi, Okada, Hiroyuki, Oba, Tatsumi, Subramanian, Karthikk, Yanai, Naoto, Pranata, Sugiri
The Industrial Control System (ICS) environment encompasses a wide range of intricate communication protocols, posing substantial challenges for Security Operations Center (SOC) analysts tasked with monitoring, interpreting, and addressing network ac
Externí odkaz:
http://arxiv.org/abs/2407.15428
Autor:
Wang, Xinyi, Antoniades, Antonis, Elazar, Yanai, Amayuelas, Alfonso, Albalak, Alon, Zhang, Kexun, Wang, William Yang
The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we introduce a
Externí odkaz:
http://arxiv.org/abs/2407.14985
Recent work on evaluating the diversity of text generated by LLMs has focused on word-level features. Here we offer an analysis of syntactic features to characterize general repetition in models, beyond frequent n-grams. Specifically, we define synta
Externí odkaz:
http://arxiv.org/abs/2407.00211
How novel are texts generated by language models (LMs) relative to their training corpora? In this work, we investigate the extent to which modern LMs generate $n$-grams from their training data, evaluating both (i) the probability LMs assign to comp
Externí odkaz:
http://arxiv.org/abs/2406.13069
Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on downstream applicat
Externí odkaz:
http://arxiv.org/abs/2406.00787