Zobrazeno 1 - 10
of 9 134
pro vyhledávání: '"Mengnan An"'
Latent representation alignment has become a foundational technique for constructing multimodal large language models (MLLM) by mapping embeddings from different modalities into a shared space, often aligned with the embedding space of large language
Externí odkaz:
http://arxiv.org/abs/2411.05316
Autor:
Shu, Dong, Du, Mengnan
In-context learning can help Large Language Models (LLMs) to adapt new tasks without additional training. However, this performance heavily depends on the quality of the demonstrations, driving research into effective demonstration selection algorith
Externí odkaz:
http://arxiv.org/abs/2410.23099
Publikováno v:
Journal of Molecular Liquids, 2024, 414: 126190
The ionic selectivity of nanopores is crucial for the energy conversion based on nanoporous membranes. It can be significantly affected by various parameters of nanopores and the applied fields driving ions through porous membranes. Here, with finite
Externí odkaz:
http://arxiv.org/abs/2410.20365
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the effectiveness o
Externí odkaz:
http://arxiv.org/abs/2410.15042
Intelligent reflecting surface (IRS) operating in the terahertz (THz) band has recently gained considerable interest due to its high spectrum bandwidth. Due to the exploitation of large scale of IRS, there is a high probability that the transceivers
Externí odkaz:
http://arxiv.org/abs/2410.08459
Large language models (LLMs) leveraging in-context learning (ICL) have set new benchmarks in few-shot learning across various tasks without needing task-specific fine-tuning. However, extensive research has demonstrated that the effectiveness of ICL
Externí odkaz:
http://arxiv.org/abs/2410.07523
Autor:
Zhu, Xiangqian, Shi, Mengnan, Yu, Xuexin, Liu, Chang, Lian, Xiaocong, Fei, Jintao, Luo, Jiangying, Jin, Xin, Zhang, Ping, Ji, Xiangyang
Atrial fibrillation is a commonly encountered clinical arrhythmia associated with stroke and increased mortality. Since professional medical knowledge is required for annotation, exploiting a large corpus of ECGs to develop accurate supervised learni
Externí odkaz:
http://arxiv.org/abs/2410.18094
Many bias mitigation methods have been developed for addressing fairness issues in machine learning. We found that using linear mixup alone, a data augmentation technique, for bias mitigation, can still retain biases present in dataset labels. Resear
Externí odkaz:
http://arxiv.org/abs/2410.01145
Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is a principle approach to denote the vector of a certain concept in the
Externí odkaz:
http://arxiv.org/abs/2410.00153
Autor:
Shi, Zeru, Mei, Kai, Jin, Mingyu, Su, Yongye, Zuo, Chaoji, Hua, Wenyue, Xu, Wujiang, Ren, Yujie, Liu, Zirui, Du, Mengnan, Deng, Dong, Zhang, Yongfeng
Large language models (LLMs) have demonstrated significant potential in the development of intelligent applications and systems such as LLM-based agents and agent operating systems (AIOS). However, when these applications and systems interact with th
Externí odkaz:
http://arxiv.org/abs/2410.11843