Trust propagation and structural containment in Multi-agent LLM pipelines
研究通过共享内存中毒和间接提示注入攻击多代理LLM系统，提出使用任务绑定签名令牌和独立验证策略来防止未授权行为，确保即使验证者被攻破也能限制执行。
0 citationsRead paper
Selected work
Representative Papers
5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs
该研究通过创建5-Dialects-BN数据集解决孟加拉语方言在自然语言处理任务中的资源不足问题，包含五种方言的6000条标注数据，支持多种NLP任务。
0 citationsRead paper
Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm
This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and imbalancing the data processing in the passes is considered an imitation of the cognitive processes observed in humans suffering from sleep deprivation. Previous research has demonstrated that sleep deprivation in the Forward-Forward algorithm has a catastrophic effect on learning efficacy. To mitigate this issue, we explore several approaches; these include alternative activation, optimized loss function, and threshold tuning. To simulate periodic rest, we reduce the number of positive passes in alternating epochs, creating short break phases. We additionally investigate the potential of caffeine-induced stimulation to enhance performance during sleep-deprived conditions. Experimental evaluations conducted on the MNIST and Fashion-MNIST datasets demonstrate that these modifications improve accuracy under the context of sleep deprivation. For example, a 2%-62% accuracy gain is observed in a severe sleep deprivation setting (16 positive or awake periods and 1 negative or sleep period). The approaches also enhance the resilience of the algorithm and its alignment with the adaptive mechanisms of human cognition.
0 citationsRead paper
To What Extent Do Large Language Models Understand Bangla Idioms?
本文构建了首个大规模孟加拉语成语基准数据集，并通过三项任务评估了大型语言模型对成语的理解能力，使用零样本和少样本提示策略。
0 citationsRead paper
TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models
为解决病理基础模型参数过多和推理成本高问题，TAP-Path通过自适应结构与token剪枝方法，在保持准确率的同时显著减少了参数量和计算量。
0 citationsRead paper
Recent publications
Latest Papers
Trust propagation and structural containment in Multi-agent LLM pipelines
研究通过共享内存中毒和间接提示注入攻击多代理LLM系统，提出使用任务绑定签名令牌和独立验证策略来防止未授权行为，确保即使验证者被攻破也能限制执行。
0 citationsRead paper
5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs
该研究通过创建5-Dialects-BN数据集解决孟加拉语方言在自然语言处理任务中的资源不足问题，包含五种方言的6000条标注数据，支持多种NLP任务。
0 citationsRead paper
Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm
This paper addresses the challenge posed by sleep deprivation in the Forward-Forward algorithm, where separating the two passes in this algorithm and imbalancing the data processing in the passes is considered an imitation of the cognitive processes observed in humans suffering from sleep deprivation. Previous research has demonstrated that sleep deprivation in the Forward-Forward algorithm has a catastrophic effect on learning efficacy. To mitigate this issue, we explore several approaches; these include alternative activation, optimized loss function, and threshold tuning. To simulate periodic rest, we reduce the number of positive passes in alternating epochs, creating short break phases. We additionally investigate the potential of caffeine-induced stimulation to enhance performance during sleep-deprived conditions. Experimental evaluations conducted on the MNIST and Fashion-MNIST datasets demonstrate that these modifications improve accuracy under the context of sleep deprivation. For example, a 2%-62% accuracy gain is observed in a severe sleep deprivation setting (16 positive or awake periods and 1 negative or sleep period). The approaches also enhance the resilience of the algorithm and its alignment with the adaptive mechanisms of human cognition.
0 citationsRead paper
To What Extent Do Large Language Models Understand Bangla Idioms?
本文构建了首个大规模孟加拉语成语基准数据集，并通过三项任务评估了大型语言模型对成语的理解能力，使用零样本和少样本提示策略。
0 citationsRead paper
TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models
为解决病理基础模型参数过多和推理成本高问题，TAP-Path通过自适应结构与token剪枝方法，在保持准确率的同时显著减少了参数量和计算量。
0 citationsRead paper