Zobrazeno 1 - 10
of 371
pro vyhledávání: '"Lian, Shiguo"'
Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities. However, hallucinations in MLLMs, where the generated text does not align with image content, continue to be a major c
Externí odkaz:
http://arxiv.org/abs/2408.01003
Autor:
Zhang, Wenjing, Xiao, Siqi, Lei, Xuejiao, Wang, Ning, Zhang, Huazheng, An, Meijuan, Yang, Bikun, Liu, Zhaoxiang, Wang, Kai, Lian, Shiguo
The rapid growth of large language models(LLMs) has emerged as a prominent trend in the field of artificial intelligence. However, current state-of-the-art LLMs are predominantly based on English. They encounter limitations when directly applied to t
Externí odkaz:
http://arxiv.org/abs/2406.18192
Autor:
Zhang, Wenjing, Lei, Xuejiao, Liu, Zhaoxiang, An, Meijuan, Yang, Bikun, Zhao, KaiKai, Wang, Kai, Lian, Shiguo
With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking com
Externí odkaz:
http://arxiv.org/abs/2406.10311
Autor:
Lian, Shiguo, Zhao, Kaikai, Liu, Xinhui, Lei, Xuejiao, Yang, Bikun, Zhang, Wenjing, Wang, Kai, Liu, Zhaoxiang
General large language models enhanced with supervised fine-tuning and reinforcement learning from human feedback are increasingly popular in academia and industry as they generalize foundation models to various practical tasks in a prompt manner. To
Externí odkaz:
http://arxiv.org/abs/2406.10307
Publikováno v:
2024 IEEE International Conference on Robotics and Automation (ICRA), 3962-3968
Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from the sourc
Externí odkaz:
http://arxiv.org/abs/2405.08434
Publikováno v:
2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 870-874
Anomaly detection without priors of the anomalies is challenging. In the field of unsupervised anomaly detection, traditional auto-encoder (AE) tends to fail based on the assumption that by training only on normal images, the model will not be able t
Externí odkaz:
http://arxiv.org/abs/2308.00429
In recent years, deep learning technology has been maturely applied in the field of object detection, and most algorithms tend to be supervised learning. However, a large amount of labeled data requires high costs of human resources, which brings abo
Externí odkaz:
http://arxiv.org/abs/2306.14106
Person counting is considered as a fundamental task in video surveillance. However, the scenario diversity in practical applications makes it difficult to exploit a single person counting model for general use. Consequently, engineers must preview th
Externí odkaz:
http://arxiv.org/abs/2303.13788
In practical applications especially with safety requirement, some hand-held actions need to be monitored closely, including smoking cigarettes, dialing, eating, etc. Taking smoking cigarettes as example, existing smoke detection algorithms usually d
Externí odkaz:
http://arxiv.org/abs/2210.06682