Zobrazeno 1 - 10
of 880 482
pro vyhledávání: '"P, Fine"'
Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and provable se
Externí odkaz:
http://arxiv.org/abs/2501.01672
Autor:
Yang, Jiaqi, Liang, Enming, Su, Zicheng, Zou, Zhichao, Zhen, Peng, Guo, Jiecheng, Ma, Wanjing, An, Kun
Decision-focused learning (DFL) offers an end-to-end approach to the predict-then-optimize (PO) framework by training predictive models directly on decision loss (DL), enhancing decision-making performance within PO contexts. However, the implementat
Externí odkaz:
http://arxiv.org/abs/2501.01874
Autor:
Abdellatif, Mohamed Hisham
Large Language Models (LLMs) have become essential tools across various domains due to their impressive capabilities in understanding and generating human-like text. The ability to accurately answer multiple-choice questions (MCQs) holds significant
Externí odkaz:
http://arxiv.org/abs/2501.01588
Human action understanding is crucial for the advancement of multimodal systems. While recent developments, driven by powerful large language models (LLMs), aim to be general enough to cover a wide range of categories, they often overlook the need fo
Externí odkaz:
http://arxiv.org/abs/2501.01245
Autor:
Jang, Wonsuk, Tambe, Thierry
Large Language Models (LLMs) have achieved remarkable success, but their increasing size poses significant challenges in memory usage and computational costs. Quantizing both weights and activations can address these issues, with fine-grained block-w
Externí odkaz:
http://arxiv.org/abs/2501.01144
Open-vocabulary segmentation aims to identify and segment specific regions and objects based on text-based descriptions. A common solution is to leverage powerful vision-language models (VLMs), such as CLIP, to bridge the gap between vision and text
Externí odkaz:
http://arxiv.org/abs/2501.00877
The ability of perceiving fine-grained spatial and temporal information is crucial for video-language retrieval. However, the existing video retrieval benchmarks, such as MSRVTT and MSVD, fail to efficiently evaluate the fine-grained retrieval abilit
Externí odkaz:
http://arxiv.org/abs/2501.00513
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, existing methods overlook a crucial issue: if the underlying foundation mo
Externí odkaz:
http://arxiv.org/abs/2412.20895
With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal that fine-tuning an existing adversarial example (AE) in feature space c
Externí odkaz:
http://arxiv.org/abs/2412.20807
Autor:
Rios, Edwin Arkel, Yuanda, Jansen Christopher, Ghanz, Vincent Leon, Yu, Cheng-Wei, Lai, Bo-Cheng, Hu, Min-Chun
Ultra-fine-grained image recognition (UFGIR) is a challenging task that involves classifying images within a macro-category. While traditional FGIR deals with classifying different species, UFGIR goes beyond by classifying sub-categories within a spe
Externí odkaz:
http://arxiv.org/abs/2501.00243